Optimized scheduling method, system and equipment for water volume of water transfer project and medium

Abstract

The invention provides an optimal scheduling method, system and equipment for the water volume of a water transfer project and a medium, and the method comprises the steps: constructing a lake and reservoir mixing system for cross-regional water transfer of a Huaiai-River North transfer project, and determining a target function and a constraint condition of a water volume optimal scheduling model by taking the minimization of the cross-regional water transfer volume as a principle; three-stage time scale layering of year, month and ten days is designed, a layered nested control feedback mechanism is adopted, and a water volume optimization scheduling model of a three-stage time scale nested structure is constructed; and based on an improved differential evolution algorithm, solving the water volume optimization scheduling model of the three-level time scale nested structure by combining incoming water forecast, water demand conditions and boundary conditions of different time scales, and obtaining an optimization scheduling scheme. By controlling a feedback mechanism, multi-time-scale water volume optimization scheduling from year to month to ten days is realized, and dynamic adjustment and optimization of a scheduling scheme are ensured, so that the utilization efficiency of water resources is improved, and the method adapts to the uncertainty of water incoming and water demand processes.

Description

Technical Field

[0001] This invention relates to the field of water conservancy construction technology, and in particular to a method, system, equipment and medium for optimizing the scheduling of water volume in water diversion projects. Background Technology

[0002] A complex transregional water resource system with lakes as its water source refers to a system that uses lakes as its core water source and connects various water sources such as rivers, reservoirs, and groundwater through a network of transregional water transfer projects (such as water conveyance channels, pumping stations, and dams). This system spans multiple administrative or geographical regions and is characterized by multi-objective coordinated scheduling needs (such as water supply, flood control, ecology, and power generation), coordination of multiple stakeholders' interests (involving different regions, departments, and stakeholders), and strong nonlinear dynamic coupling. Its core task is to achieve efficient allocation of lake water resources and balanced spatiotemporal utilization of regional water resources through optimized scheduling.

[0003] Currently, complex cross-regional water resource allocation systems relying on lakes as water sources face three major challenges: insufficient system generalization, often neglecting the water storage potential of river channels during modeling; fragmented optimization across time scales, lacking coupling and coordination between time scales; and performance bottlenecks in basic optimization algorithms, such as the differential evolution algorithm's tendency to premature convergence and difficulty in guaranteeing global optimality. Therefore, an effective method for optimizing the allocation of water resources in water transfer projects is urgently needed to address these issues. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed to provide a method, system, equipment and medium for optimizing the scheduling of water volume in water diversion projects to overcome or at least partially solve the above problems.

[0005] To achieve the above and other related objectives, the present invention provides a method for optimizing the scheduling of water volume in a water diversion project, the method comprising: Construct a lake-reservoir hybrid system for cross-regional water transfer in the Huaihe River North Diversion Project, and determine the objective function and constraints of the water volume optimization scheduling model based on the principle of minimizing the cross-regional water transfer volume. The design incorporates a three-tiered time scale of year, month, and day, and employs a nested control feedback mechanism to construct a water volume optimization scheduling model with a three-tiered time scale nested structure. Based on the improved differential evolution algorithm, and combined with water inflow forecasts, water demand and boundary conditions at different time scales, the water quantity optimization scheduling model with the three-level time scale nested structure is solved to obtain the optimized scheduling scheme.

[0006] Optionally, the construction of the lake-reservoir hybrid system for inter-regional water transfer in the Huaihe River North Diversion Project includes: The source lakes suitable as water sources within the study area of ​​the Huaihe River North Diversion Project were identified, and the water diversion route of the Huaihe River North Diversion Project was constructed based on the hydrological and water resource conditions, water demand, and water conservancy projects within the study area. The study area includes three main regions: Bengbu District, Suzhou District, and Huaibei District. In the water diversion route, a river with a large water storage capacity is selected as the water intake reservoir, which is connected with the source lake to form a lake-reservoir hybrid system for cross-regional water diversion of the Huaihe River to the North China Water Diversion Project; wherein, the water storage capacity of the river is determined by the upper and lower limits of the river water level.

[0007] Optionally, the objective function and constraints of the water allocation optimization model, determined based on the principle of minimizing inter-regional water transfer, include: The objective function of the water optimization model is to minimize the water supply of the source lake during the preset scheduling period, and the constraints of the water optimization scheduling model are set. The constraints include water balance constraints, upper and lower limits of water level constraints, water demand constraints, available water constraints, pumping capacity constraints, and variable non-negativity constraints.

[0008] Optionally, the water quantity optimization scheduling model, which employs a hierarchical nested control feedback mechanism to construct a three-level time-scale nested structure, includes: Based on the three-level time scale of year, month, and day, and in combination with the objective function and the constraints, a separate water quantity optimization scheduling model is established for each time scale. By combining water quantity optimization scheduling models at various time scales and constructing a three-level time scale nested water quantity optimization scheduling model through a hierarchical nested control feedback mechanism.

[0009] Optionally, the step of solving the three-level time-scale nested water allocation optimization model based on the improved differential evolution algorithm, combined with inflow forecasts, water demand conditions, and boundary conditions at different time scales, includes: Set the initial parameters of the improved differential evolution algorithm, and encode and constrain the decision variables of the problem-solving problem in the three-level time-scale nested water quantity optimization scheduling model; Determine the input conditions for the water quantity optimization scheduling model with the nested structure of the three-level time scale; wherein, the input conditions include inflow forecast, water demand forecast and boundary conditions of the three-level time scale; Based on the inflow forecast, demand forecast, and boundary conditions of the three time scales, and combined with the improved differential evolution algorithm and control feedback mechanism, the water quantity optimization scheduling model of the nested structure of the three time scales is solved to obtain the optimized scheduling scheme.

[0010] Optionally, the step of setting the initial parameters of the improved differential evolution algorithm and encoding individual information and performing constraint processing on the decision variables of the water quantity optimization scheduling model with the three-level time scale nested structure includes: Set the initial parameters for the improved differential evolution algorithm; wherein, the initial parameters include the vector dimension of the decision variables, the population size, and the total number of iterations; the decision variables include the water supply of Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section at various time periods; According to the real number encoding rules, the decision variables are mapped to the gene loci of individuals to establish a one-to-one index relationship and form an encoded individual; For coded individuals that do not meet the boundary constraints, the difference method is used to iteratively calculate the pairing difference between feasible and infeasible solutions in the current population, and gradually correct infeasible solutions until all of them enter the feasible region and meet the constraints.

[0011] Optionally, after the step of solving the water quantity optimization scheduling model with the three-level time scale nested structure, the method further includes: Calculate the supply-demand ratio of the optimized scheduling scheme, and evaluate the optimized scheduling scheme based on the supply-demand ratio.

[0012] Secondly, the present invention also provides an optimized scheduling system for water volume in water diversion projects, the system comprising: The module is used to construct the lake and reservoir hybrid system for cross-regional water transfer in the Huaihe River North Diversion Project, and to determine the objective function and constraints of the water volume optimization scheduling model with the principle of minimizing the cross-regional water transfer volume. The module is used to design a three-level time scale hierarchy of year, month, and day, and adopts a hierarchical nested control feedback mechanism to build a water volume optimization scheduling model with a three-level time scale nested structure. The solution module is used to solve the water quantity optimization scheduling model with a three-level time scale nested structure based on the improved differential evolution algorithm, combined with water inflow forecasts, water demand and boundary conditions at different time scales, to obtain the optimized scheduling scheme.

[0013] Thirdly, the present invention provides an electronic device comprising: a memory and a processor; the memory for storing a computer program; and the processor for executing the computer program stored in the memory to cause the electronic device to perform the steps of the water diversion project water volume optimization scheduling method as described above.

[0014] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the steps of the water allocation optimization scheduling method for water diversion projects as described above.

[0015] The above-described one or more technical solutions provided by this invention can have the following advantages or at least achieve the following technical effects: This invention utilizes an improved differential evolution algorithm and a control feedback mechanism to achieve multi-timescale water quantity optimization scheduling from year to month to ten-day period, ensuring dynamic adjustment and optimization of the scheduling scheme, thereby improving water resource utilization efficiency and adapting to the uncertainties of water inflow and demand processes. Attached Figure Description

[0016] Figure 1 The diagram shows a flowchart of an optimized water allocation method for a water diversion project according to an embodiment of the present invention.

[0017] Figure 2 The diagram shows the geographical layout of the Huaihe River North Diversion Project in one embodiment of the present invention.

[0018] Figure 3 The diagram shown is a simplified structural diagram of the Huaihe River North Diversion Project in one embodiment of the present invention.

[0019] Figure 4 This is a schematic diagram illustrating the layering of three time scales—year, month, and ten-day period—in one embodiment of the present invention.

[0020] Figure 5 The diagram shows the operational structure of the "control-feedback" mechanism in one embodiment of the present invention.

[0021] Figure 6 The diagram shows a schematic representation of the computational flow of the improved differential evolution algorithm in one embodiment of the present invention.

[0022] Figure 7 The diagram shows a flowchart of solving a three-level time-scale nested water quantity optimization scheduling model in one embodiment of the present invention.

[0023] Figure 8 The diagram shown is a schematic diagram of the water level and reservoir capacity curve of Xiangjian Lake, the water source for water diversion, in one embodiment of the present invention.

[0024] Figure 9 The diagram shown is a schematic diagram of the water level and reservoir capacity curve of the Lousong-Erpu River section, the water source for water diversion, in one embodiment of the present invention;

[0025] Figure 10 The diagram shown is a schematic diagram of the water level and reservoir capacity curve of the Sipu-Houwang River section, a water source for water diversion, in one embodiment of the present invention.

[0026] Figure 11 The diagram shown is a schematic diagram of the water supply process of each water source in one embodiment of the present invention;

[0027] Figure 12 This is a schematic diagram showing the information encoding of the i-th individual in the g-th generation population according to an embodiment of the present invention.

[0028] Figure 13 The diagram shows a functional module schematic of a water diversion project water volume optimization scheduling system in one embodiment of the present invention.

[0029] Figure 14 The diagram shown is a schematic representation of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0030] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0031] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0032] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0033] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0034] Unless otherwise stated, the term "multiple" means two or more.

[0035] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0036] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0037] The technical solutions of the present invention will now be described in detail with reference to the accompanying drawings.

[0038] Please see Figure 1 An embodiment of the present invention provides a method for optimizing the scheduling of water volume in a water diversion project, the method including the following steps S10~S30: Step S10: Construct a lake-reservoir hybrid system for cross-regional water transfer in the Huaihe River North Diversion Project, and determine the objective function and constraints of the water volume optimization scheduling model based on the principle of minimizing cross-regional water transfer volume.

[0039] The Huai River North Diversion Project is a cross-regional water resource allocation project aimed at solving the long-term water shortage problem in northern Anhui Province (including Suzhou and Huaibei cities). Its core operating mechanism is as follows: using Xiangjian Lake as a key regulation and storage node, when the current water volume is insufficient, water is drawn from the Huai River through the Wuhe Station to supplement it; then, through eight pumping stations connected in series (Wuhe Station, Guzhen Station, Lousong Station, Erpu Station, Sipu Station, Houwang Station, Jiawo Station, and Daishankou Station), the water is gradually lifted and transported to the water-receiving areas such as Suzhou, Huaibei, and Xiaoxian.

[0040] Please see Figure 2-3 , Figure 2 The map shows the spatial geographical distribution of the Huaihe River North Diversion Project, the main water bodies (lakes and rivers), and the locations of pumping stations. Its main contents include: the area within Anhui Province involved in the project (including Suzhou and Huaibei), with different colored fills representing different administrative regions; the main water bodies (such as Xiangjian Lake); the pumping station facilities (standardizing the eight key water pumping stations along the project route, including Wuhe Station, Guzhen Station, Lousong Station, Erpu Station, Sipu Station, Houwang Station, Jiawo Station, and Daishankou Station); and the water transmission route (water is drawn from Wuhe Station, passes through Guzhen Station, Lousong Station, Erpu Station, Sipu Station, and Houwang Station, and is finally transported to Huaibei and Xiaoxian through Jiawo Station and Daishankou Station).

[0041] Figure 3 The diagram illustrates the generalized structure of the Huaihe River North Diversion Project, mainly including the project's system components (water source, pumping stations, lakes / storage nodes, water users, rivers / channels, and control gates), water flow path (water is drawn from Wuhe Station, passes through Guzhen Station → Lousong Station → Erpu Station → Sipu Station → Houwang Station, and finally transported to users in Huaibei and Xiaoxian via Jiawo Station → Daishankou Station), pumping station functional zones, and user connection relationships; Xiangjian Lake in the diagram serves as a storage reservoir, receiving water drawn from Houwang Station and regulating it.

[0042] The lake-reservoir hybrid system refers to the system in the Huaihe River North Diversion Project that integrates Xiangjian Lake with other waterways (such as the Sipu-Houwang section) into a unified whole for joint scheduling and management. Its core objective is to achieve more efficient and sustainable water resource allocation by optimizing the combination of various local water resources (lake storage capacity and river transport capacity).

[0043] A water resource optimization scheduling model is a mathematical model used to represent the determination of the optimal water resource allocation scheme under specific time scales (such as year, month, ten-day period, day) and a series of constraints (such as water level limits, water supply limits, water demand requirements, etc.) to achieve specific objectives (such as minimizing water shortage, maximizing water supply benefits, minimizing water transfer costs, etc.). Its core components include an objective function and constraints. By setting the objective function and constraints, the water resource optimization scheduling model uses optimization algorithms to find the optimal solution in complex systems, providing a scientific basis for practical engineering scheduling. Essentially, it seeks the optimal resource allocation strategy while satisfying all realistic constraints.

[0044] An objective function is a mathematical expression used to represent maximization or minimization. Common types of objective functions include minimizing water shortage, minimizing water transfer costs, maximizing water supply guarantee rate, and multi-objective integrated optimization. In this embodiment, the objective function is to minimize inter-regional water transfer. Its expression can be: (1) In the formula, f represents the amount of water transferred across regions; The value represents the water supply volume from the source lake during time period t, expressed in tens of thousands of m³; T represents the number of time periods.

[0045] Constraints are used to represent the rules and restrictions that the water allocation optimization model must follow, ensuring that the obtained allocation scheme is feasible, safe, and reasonable in reality. They mainly include: water balance constraints (conservation of water inflow and outflow within the system at different times), upper and lower water level constraints (lake and river water levels must be within safe limits), water demand constraints (meeting the minimum water demand requirements of the water supply area at different times), available water constraints (water supply must not exceed the maximum available water volume of lakes / rivers), pumping capacity constraints (pump station water delivery must not exceed the maximum pumping capacity under rated power), and variable non-negativity constraints (all variables must conform to physical meaning).

[0046] In its implementation, based on the engineering conditions, water resources, and water supply area of ​​the Huaihe River North Diversion Project, a series of inter-regional water transfer systems is constructed, with Xiangjian Lake as the core storage node, the Lousong-Erpu and Sipu-Houwang river sections as water conveyance channels, the Guzhen Station to Daishankou Station as power nodes, and Bengbu, Suzhou, and Huaibei as water receiving units. The water volume optimization scheduling of this system uses minimizing the water supply from the inter-regional lake source (Xiangjian Lake) during the scheduling period as the objective function of the water volume optimization scheduling model. This model must satisfy a series of constraints to ensure the feasibility of the scheme. These constraints may include water balance constraints, upper and lower water level constraints, water demand constraints, available water constraints, pumping capacity constraints, and variable non-negativity constraints. By minimizing the combined water supply, local water resources are prioritized, while ensuring that all engineering and water demand constraints are met.

[0047] Step S20: Design a three-level time scale hierarchy of year, month, and day, and adopt a hierarchical nested control feedback mechanism to construct a water quantity optimization scheduling model with a three-level time scale nested structure.

[0048] The water allocation optimization scheduling model, with its three-tiered time-scale nested structure, divides the scheduling period into three levels: year, month, and day. These levels are then matched with long-term, medium-term, and short-term hydrological forecasts, forming a nested system of "coarse-grained planning at the upper level and fine-grained execution at the lower level." To better handle uncertainties at different time scales (such as long-term trends, seasonal variations, and short-term fluctuations) and to achieve nested optimization of the "control-feedback" mechanism, a three-tiered time-scale structure (year, month, day) was designed within the water allocation optimization scheduling model. Each level of the model optimizes scheduling based on the hydrological forecast results for its corresponding time scale.

[0049] The three-tiered time scale of year, month, and day is used to represent the refined and intelligent scheduling management of complex water resource systems in water optimization scheduling models. This is achieved by dividing the scheduling period into different time scales such as year, month, ten-day period, and day, and matching them with hydrological forecast information of corresponding accuracy (such as long-term, medium-term, and short-term forecasts). Please refer to [link / reference]. Figure 4 , Figure 4 It displays a three-level time scale hierarchy of year, month, and day, specifically: The first level (year) uses the year as the scheduling period, dividing the whole year into 12 months; Figure 4 The text shows a one-year time span, representing long-term scheduling and long-term hydrological forecasting.

[0050] The second layer (monthly) uses the month as the scheduling period, dividing each month into three ten-day periods; Figure 4 The "one month" is divided into three phases (1, 2, and 3 ten-day periods), representing medium-term scheduling and medium-term hydrological forecasting.

[0051] The third layer (ten-day period) uses ten days as the scheduling period, dividing each ten-day period into 10 days; Figure 4 The term "ten-day period" is divided into 10 days, representing short-term scheduling and short-term hydrological forecasting.

[0052] A control feedback mechanism is used to represent how the upper-level model guides the lower-level model's operation through control conditions, and the lower-level model corrects the upper-level model's strategy based on actual data. The two form a closed loop during rolling operation, ensuring that water quantity optimization scheduling models at different time scales can both adhere to long-term goals and adapt to short-term changes, ultimately achieving optimal allocation of overall water resources. Specifically: The control mechanism involves the upper-level model providing control conditions (such as the control water level to be reached at the end of the scheduling period) for the lower-level model based on the optimization objectives of the entire scheduling period or the residual period. These conditions serve as boundary conditions and objective guidelines for the operation of the lower-level model.

[0053] The feedback mechanism allows the lower-level model to feed back real-time information such as the actual observed water level and the inflow predicted by the lower-level model to the upper-level model when it reaches the current moment. The upper-level model then updates its own scheduling scheme for the remaining time period based on this information, thereby achieving dynamic optimization and adjustment for future time periods.

[0054] Please see Figure 5 , Figure 5 The operational structure of the control feedback mechanism is demonstrated. The upper-level model guides the lower-level model through "control" (providing the end-of-period control water level), while the lower-level model corrects the upper-level model's residual period plan through "feedback" (transmitting real-time water level and predicted inflow), forming a two-way optimization closed loop between the upper and lower levels. After the lower-level model completes its operation for a period, its actual water resource situation at the end of the period (such as actual water level and actual inflow) will be updated to reflect the water resource status at the beginning of the upper-level model's residual period (the beginning of the next period).

[0055] In practical implementation, a three-level time scale can be designed: year (long-term), month (medium-term), and ten-day period (short-term). Specifically, the first level (year) uses the year as the scheduling period and the month as the forecast (the scheduling period is usually 12 periods); the second level (month) uses the month as the scheduling period and the ten-day period as the forecast (the scheduling period is 1, 2, and 3 ten-day periods, 3 periods); the third level (ten-day period) uses the ten-day period as the scheduling period and the day as the forecast (the scheduling period is usually 10 periods). Based on this, water optimization models at each time scale are constructed separately, and a hierarchical nested control feedback mechanism is adopted to finally form a water optimization scheduling model with a three-level time scale nested structure.

[0056] Step S30: Based on the improved differential evolution algorithm, and combined with water inflow forecasts, water demand and boundary conditions at different time scales, solve the water quantity optimization scheduling model of the three-level time scale nested structure to obtain the optimized scheduling scheme.

[0057] Among them, the improved differential evolution algorithm is used to indicate that it is an optimization and upgrade of the traditional differential evolution algorithm. The core improvement strategy is to enhance performance through two types of improvement strategies: The parameter adaptive adjustment strategy introduces an adaptive quadratic scaling factor F and an adaptive quadratic crossover probability factor CR to improve algorithm performance. The calculation formulas are expressed as follows: (2) (3) In the formula, F represents the adaptive quadratic scaling factor, which controls the step size of differential mutation; CR represents the adaptive quadratic crossover probability; t represents the current generation; and T represents the maximum generation.

[0058] The adaptive quadratic scaling factor F gradually decreases within the range [0.55, 1] ​​as the number of generations increases. Its core function is to control the step size of differential mutation. In the early stages of evolution, F is larger to maintain population diversity and increase global search capability. In the later stages, F shrinks to reduce the step size of the differential mutation, thus accelerating local convergence and balancing the algorithm's global exploration and local exploitation performance. The adaptive quadratic crossover rate CR increases within the range (0, 1) as the number of generations increases. The improvements to F and CR ensure that the algorithm achieves the global optimum during evolution, maintains rich population diversity and strong global search capability in the early stages, and allows for a gradual increase in search speed in the later stages.

[0059] The triangular mutation strategy, based on traditional differential mutation, uses mutation probabilities... The dynamic selection of mutation mode can be expressed as follows: (4) (5) (6) (7) (8) In the formula, Represents the variable, the mutation result of the i-th individual in the g-th generation of the population; Represents a random individual, specifically 3 individuals randomly selected from the population in the g-th generation; This represents the mutation probability and is a threshold used to determine whether to employ the triangular mutation strategy. The weighting coefficient represents the weight of an individual's contribution to the variation, and is determined by the individual's objective function value. Represents a random number; This represents the objective function.

[0060] like The system employs a triangular mutation formula, combining information from three random individuals and using fitness-weighted coefficients for intelligent mutation to enhance search targeting; otherwise, it uses a standard difference mutation formula. It retains the global exploration feature of traditional mutations.

[0061] Please see Figure 6 , Figure 6 The diagram illustrates the computational flow of the improved differential evolution algorithm. Through the combined effect of improved strategies, the improved differential evolution algorithm can better balance global and local search during the optimization process, thereby achieving better optimization performance.

[0062] Water inflow forecasting is used to represent the input conditions of each layer of the water allocation optimization scheduling model with a three-level nested time scale. Specifically, hydrological models such as SWAT are used to forecast the water inflow of Xiangjian Lake and the Sipu-Houwang River section at long, medium, and short time scales. Specifically, the long-term forecast period is annual, and the forecast period is monthly; the medium-term forecast period is monthly, and the forecast period is ten days; the short-term forecast period is ten days, and the forecast period is daily.

[0063] Water demand information is used to represent the input conditions of each layer of the water quantity optimization scheduling model in the three-level nested time scale structure. It corresponds to the water demand forecast results of each water-receiving area according to the long-term, medium-term, and short-term time scales. Specifically, the long-term (year-month) forecast period is one year, and the forecast period is one month; the medium-term (month-ten-day) forecast period is one month, and the forecast period is one ten-day; the short-term (ten-day-day) forecast period is one ten-day, and the forecast period is one day.

[0064] Boundary conditions represent the core constraints of each layer in a three-level nested water quantity optimization scheduling model, mainly including: initial water level, control water level at the end of the scheduling period, upper and lower limit water levels, and initial water storage. Furthermore, boundary conditions can be adjusted according to actual engineering needs to ensure the model conforms to the constraints of real-world scenarios and meets scheduling objectives at different time scales.

[0065] The optimized scheduling scheme can represent the output of the water volume optimization scheduling model with a three-level time scale nested structure. It mainly includes the water diversion plans of Xiangjian Lake, Erpu-Lousong River section, and Sipu-Houwang River section at different time scales (daily, ten-day, and monthly).

[0066] In practical implementation, the input conditions (long-term, medium-term, and short-term inflow forecasts, water demand, and boundary conditions) of the three-level nested time-scale water optimization scheduling model can be determined first. Then, the improved differential evolution algorithm combined with the control feedback mechanism is used to solve the model, and finally the optimized scheduling schemes corresponding to each level of the model are obtained. Specifically, the optimized scheduling schemes for Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section at different time scales (daily, ten-day, and monthly) are obtained. By utilizing the advantages of different time scales, the core mechanism of long-term coordination and short-term precision is achieved, which significantly improves the water optimization scheduling efficiency of the entire lake and reservoir mixed system.

[0067] Furthermore, in one embodiment, step S10 may include sub-steps S101~S102: Sub-step S101: Determine the source lakes suitable as water sources within the research area of ​​the Huaihe River North Diversion Project, and construct the water diversion route of the Huaihe River North Diversion Project based on the hydrological and water resources conditions, water demand conditions, and water conservancy project conditions within the research area; wherein, the research area includes three general areas: Bengbu District, Suzhou District, and Huaibei District; Sub-step S102: Select a river with a large water storage capacity in the water diversion route as a water intake reservoir, and connect it with the source lake to form a lake-reservoir hybrid system for cross-regional water diversion of the Huaihe River to the North China Water Diversion Project; wherein, the water storage capacity of the river is determined by the upper and lower limits of the river water level.

[0068] The water diversion route is defined as follows: Xiangjian Lake → Guzhen Station → Lousong Station → Erpu Station → Sipu Station → Houwang Station → Jiawo Station → Daishankou Station. Water from Xiangjian Lake is transported northward to the water supply areas along the route through the aforementioned cascade pumping stations.

[0069] The study area is defined as three main regions: Bengbu District, Suzhou District, and Huaibei District, based on the administrative divisions along the Huaihe River North Diversion Project. For further detailed analysis, the main regions need to be subdivided into several sub-regions based on the project's cascade pumping stations (such as Guzhen Station and Lousong Station), covering the pumping station nodes involved in the water diversion route and their surrounding water supply areas. Depending on actual needs, sub-regions can be further subdivided based on the corresponding cascade pumping stations of the Huaihe River North Diversion Project. The generalized users corresponding to the calculation units are shown in Table 1.

[0070]

[0071] Table 1. Generalized users corresponding to computing units

[0072] River storage capacity refers to the initial water storage in the Lousong-Erpu and Sipu-Houwang river sections, and its source is the "water volume intercepted by upstream flood receding". It should be noted that during the water diversion period, the water volume of Xiangjian Lake will not be used to replenish the storage capacity of these two river sections, and the impact of its initial storage capacity on water diversion must be considered independently.

[0073] In practical implementation, suitable source lakes within the Huaihe River North Diversion Project study area can be determined based on project conditions, water resources, and water supply area conditions (in actual water diversion scenarios, the storage capacity of Xiangjian Lake can basically meet the water demand along the Huaihe River North Diversion Project route, and the Wuhe Station is rarely used; therefore, the water diversion link from Wuhe to Xiangjian Lake is not considered in this case). Then, combining the hydrological and water resource conditions, water demand, and water conservancy projects within the study area, the water diversion route of the Huaihe River North Diversion Project can be constructed. Subsequently, rivers with larger storage capacities can be selected from the water diversion route as intake reservoirs (their storage capacity is determined by the river level and is subject to upper and lower limits), and these reservoirs can be connected in series with the source lakes, ultimately forming a lake-reservoir hybrid system for cross-regional water diversion in the Huaihe River North Diversion Project. Thus, through the selection of source lakes, the construction of water diversion routes, and the system design of connecting reservoirs, a balance can be achieved in water source stability, orderly water transfer, and flexible regulation, providing fundamental support for the efficient operation of the Huaihe River North Diversion Project.

[0074] Furthermore, in one embodiment, step S10 may further include sub-step S103: Sub-step S103: The objective function of the water optimization model is to minimize the water supply from the source lake during the preset scheduling period, and the constraints of the water optimization scheduling model are set. The constraints include water balance constraints, upper and lower limits of water level constraints, water demand constraints, available water constraints, pumping capacity constraints, and non-negativity constraints of variables.

[0075] Specifically, the objective functions at different time scales, such as year, month, and ten-day period, include: ① Annual time scale (9) ② Monthly time scale (10) ③ Ten-day time scale (11) In the formula, These represent forecast scheduling periods (unit time periods) at the year, month, and ten-day time scales, respectively, with time scales of month, ten-day period, and day. These represent the number of model periods on the yearly, monthly, and ten-day time scales, respectively. The yearly time scale Ta is 12 (corresponding to 12 months), the monthly time scale Tm is 3 (corresponding to the first, middle, and last ten days), and the ten-day time scale Tten is at least 8 (e.g., the last ten days of February) and at most 11 (e.g., the last ten days of long months such as January and March, due to the large number of days). The number of periods for the first, middle, and last ten days of other months is 10. The numbers represent the water supply volume of Xiangjian Lake during each forecast scheduling period (unit: 10,000 m³); W represents the water supply volume.

[0076] Constraints may include water balance constraints, upper and lower water level constraints, water demand constraints, available water supply constraints, pumping capacity constraints, and variable non-negativity constraints. Specifically, they include: ①Water balance constraints of Xiangjian Lake: (12) In the formula, represent the initial and final water storage volumes of Xiangjian Lake at the end of time period t, respectively; These represent the inflow and outflow of water into Xiangjian Lake during time period t, respectively.

[0077] ② River water balance constraints (except for the Sipu-Houwang section) (13) In the formula, These represent the initial and final water storage volumes of the j-th river channel during time period t, respectively. These represent the water lifting flow rate of the downstream pumping station and the water pumping flow rate of the upstream pumping station (water is transported from the downstream to the upstream) of the river section, respectively. Indicates a long period of time; This represents the water supply volume of the j-th river segment to the corresponding water-receiving area; This represents the amount of water lost due to evaporation and seepage in the j-th river channel during the t-th time period.

[0078] ③ Water balance constraints in the Sipu-Houwang section (14) In the formula, These represent the initial and final water storage volumes in the Sipu-Houwang section during time period t, respectively. This indicates the pumping flow rate at Sipu Station; This indicates the water flow rate drawn from Houwang Station; Indicates a long time period; This represents the total amount of water flowing into the Sipu-Houwang River section from Sipu Station during time period t. This represents the total amount of water flowing downstream to Houwang Station in the Sipu-Houwang section during time period t. This indicates the water supply volume of the Sipu-Houwang River section to the corresponding water-receiving area; This represents the inflow of the Wangyin River and the Nantuo River within the Sipu-Houwanghe section at time t. This represents the total inflow volume of the Sipu-Houwang River section during time period t. This represents the water loss due to evaporation and seepage during the t-th time period of the Sipu-Houwang section.

[0079] ④ Water level limits of Xiangjian Lake (15) In the formula, This represents the water level of Xiangjian Lake during time period t. This represents the lower limit water level of Xiangjian Lake in time period t, which is the dead water level of the lake. This represents the upper limit water level of Xiangjian Lake during time period t. During the flood season, the flood limit water level is used, and during the non-flood season, the normal storage water level is used.

[0080] ⑤ River channel operating water level constraints (16) (17) In the formula, These represent the water levels in the inlet and outlet pools of the i-th pumping station during time period t, respectively. These represent the minimum operating water levels of the inlet and outlet pools of the i-th stage pumping station, respectively. These represent the highest operating water levels at the inlet and outlet of the i-th pumping station, respectively.

[0081] ⑥ Water demand constraints (18) In the formula, This represents the water supply volume of the j-th river segment to the corresponding water-receiving area during time period t; This represents the water demand of the j-th water-receiving area during the t-th time period.

[0082] ⑦ Water supply constraints (19) In the formula, This represents the water supply volume of the j-th river segment to the corresponding water-receiving area during time period t; This represents the available water volume in the j-th river segment during the t-th time period.

[0083] ⑧ Pumping capacity constraints (20) In the formula, This represents the pumping (lifting flow rate) of the i-th level pumping station during time period t. This represents the maximum pumping capacity of the i-th level pumping station.

[0084] ⑨ Non-negativity constraint for variables: In the water allocation model, variables (such as water allocation volume, water storage volume, pump station flow rate, etc.) are required to be non-negative to ensure that they conform to physical meaning.

[0085] In practical implementation, the principle of "minimizing inter-regional water transfer" can be adopted. The objective function of the water optimization scheduling model is to minimize the water supply from the source lakes during the preset scheduling period, and constraints are set for this water optimization scheduling model. Specific constraints include water balance constraints, upper and lower water level constraints, water demand constraints, available water constraints, pumping capacity constraints, and variable non-negativity constraints. Thus, by minimizing the lake water supply (reducing inter-regional water transfer) and combining it with strict constraints, the scheduling objectives of prioritizing water conservation and balancing supply and demand can be achieved, taking into account both engineering feasibility and economy.

[0086] Furthermore, in one embodiment, after step S30, the method may further include step S40: Step S40: Calculate the supply-demand ratio of the optimized scheduling scheme, and evaluate the optimized scheduling scheme based on the supply-demand ratio.

[0087] The supply-demand ratio is a core indicator used to measure the degree of matching between the actual water supply (i.e., the water supply minimized in the objective function) and the total water demand of the water supply area (the sum of the total water demand of the water supply area during the scheduling period) during the scheduling period. Its evaluation logic is as follows: A supply-demand ratio of approximately 100% indicates that the optimized scheduling scheme perfectly matches the water demand, satisfying the water supply needs without wasting water resources. A supply-demand ratio greater than 100% indicates that the water supply exceeds the demand, which, while ensuring water supply, creates the risk of idle water resources (it is necessary to check whether the "minimize water transfer" objective is violated). A supply-demand ratio of less than 100% indicates that the water supply is insufficient and cannot meet the water demand (it is necessary to check whether the constraints, such as the available water supply or pumping capacity, have been exceeded).

[0088] Furthermore, after evaluating and optimizing the scheduling scheme based on the supply-demand ratio, if the supply-demand ratio is abnormal (>100% or <100%), the optimized scheduling scheme is adjusted according to the supply-demand ratio. If the supply-demand ratio is >100%, the objective function can be modified to reduce the water supply; if the supply-demand ratio is <100%, the water supply can be increased, constraints can be relaxed, etc.

[0089] In practical implementation, after obtaining the optimized scheduling schemes of each layer in the three-level time-scale nested water optimization scheduling model, the supply-demand ratio of the optimized scheduling scheme can be calculated. This supply-demand ratio can then be used to determine whether the corresponding optimized scheduling scheme achieves the supply-demand balance target. Thus, by quantifying the matching degree of the optimized scheduling scheme using the supply-demand ratio, the multi-dimensional goals of "water conservation, safety, economy, and collaboration" can ultimately be achieved.

[0090] In this embodiment, by utilizing an improved differential evolution algorithm and a control feedback mechanism, multi-timescale water quantity optimization scheduling from year to month to ten-day period is achieved, ensuring dynamic adjustment and optimization of the scheduling scheme, thereby improving water resource utilization efficiency and adapting to the uncertainty of water inflow and demand processes.

[0091] Based on the foregoing embodiments, a second embodiment of the method for optimizing the scheduling of water volume in water diversion projects according to the present invention is proposed. In this embodiment, step S20 may include the following sub-steps S201~S203: Sub-step S201: Based on the three-level time scales of year, month, and day, and in conjunction with the objective function and the constraints, establish separate water quantity optimization scheduling models for each time scale.

[0092] The constraints at different time scales (year, month, and ten-day period) are as follows: ① Water balance constraints of Xiangjian Lake Annual timescale (twenty one) Monthly timescale (twenty two) Ten-day time scale (twenty three) In the formula, These represent the water storage volume at the end of each forecast scheduling period (month, ten-day period, day) of Xiangjian Lake; These represent the initial water storage volume of Xiangjian Lake during each forecast scheduling period (month, ten-day period, day); These represent the inflow of water into Xiangjian Lake during each forecast scheduling period (month, ten-day period, day); These represent the outflow of water from Xiangjian Lake during each forecast scheduling period (month, ten-day period, day).

[0093] ② River water balance constraints (except for the Sipu-Houwang section) Annual timescale (twenty four) Monthly timescale (25) Ten-day time scale (26) In the formula, They represent the j-th channel and the j-th channel respectively. Water storage at the end of a time period (month, ten-day period, day); They represent the j-th channel and the j-th channel respectively. Initial water storage volume for different time periods (month, ten-day period, day); These represent the downstream pumping stations of the j-th river segment. Average water pumping flow rate over a given period (month, ten-day period, day); These represent the upstream pumping stations of the j-th river segment. Average water pumping flow rate over a given period (month, ten-day period, day); These represent time periods of months, ten-day periods, and days, respectively. These represent the monthly, ten-day, and daily water supply volumes for the water-receiving area corresponding to the j-th river segment, respectively. They represent the j-th river segment and the th... Average evaporation and water loss over a period of time (month, ten-day period, day).

[0094] ③ Water balance constraints in the Sipu-Houwang section Annual timescale (27) Monthly timescale (28) Ten-day time scale (29) In the formula, They represent the first section of the Sipu-Houwang River. Initial water storage volume for different time periods (month, ten-day period, day); They represent the first section of the Sipu-Houwang River. Water storage at the end of a time period (month, ten-day period, day); They respectively represent the Houwang Station No. Average water pumping flow rate over a given period (month, ten-day period, day); They represent the fourth station. Average water pumping flow rate over a given period (month, ten-day period, day); These represent the length of time periods, namely months, ten-day periods, and days; These represent the monthly, ten-day, and daily water supply volumes for the corresponding water-receiving area of ​​the Sipu-Houwang River section, respectively. They respectively represent the Wangyin River and the Nantuo River in the Sipu-Houwang River section. Average inflow over a period of time (month, ten-day period, day); They represent the first section of the Sipu-Houwang River. Average evaporation and water loss over a period of time (month, ten-day period, day).

[0095] ④ Water level limits of Xiangjian Lake Annual timescale (30) Monthly timescale (31) Ten-day time scale (32) In the formula, They represent the first Xiangjian Lake. Water level for different time periods (month, ten-day period, day); They represent the first Xiangjian Lake. The lower limit water level for a given period (month, ten-day period, day) is taken as the dead water level of the lake. They represent the first Xiangjian Lake. The upper limit water level for a specific time period (month, ten-day period, day) is taken during the flood season and the normal storage water level is taken during the non-flood season.

[0096] ⑤ River channel operating water level constraints Annual timescale (33) Monthly timescale (34) Ten-day time scale (35) In the formula, These represent the i-th level pump station and the i-th level pump station. Water level in the inlet pool during different time periods (month, ten-day period, day); These represent the i-th level pump station and the i-th level pump station. Water level in the outlet pool during different time periods (month, ten-day period, day); These represent the minimum operating water levels of the inlet and outlet pools of the i-th stage pumping station, respectively. These represent the highest operating water levels at the inlet and outlet of the i-th pumping station, respectively.

[0097] ⑥ Water demand constraints Annual timescale (36) Monthly timescale (37) Ten-day time scale (38) In the formula, They represent the j-th river segment and the th... Water supply volume for the corresponding water-receiving area during the specified time period (month, ten-day period, day); They represent the j-th river segment and the th... Water demand in the corresponding water-receiving area for a given period of time (month, ten-day period, day).

[0098] ⑦ Water supply constraints Annual timescale (39) Monthly timescale (40) Ten-day time scale (41) In the formula, They represent the j-th river segment and the th... Water supply volume for the corresponding water-receiving area during the specified time period (month, ten-day period, day); They represent the j-th river segment and the th... Water availability for different time periods (month, ten-day period, day).

[0099] ⑧ Pumping capacity constraints Annual timescale (42) Monthly timescale (43) Ten-day time scale (44) In the formula, These represent the i-th level pump station and the i-th level pump station. Pumping (lifting) flow rate for a given period (month, ten-day period, day); These represent the i-th level pump station and the i-th level pump station. Maximum pumping capacity for a given period (month, ten-day period, day).

[0100] ⑨ Non-negativity constraint: All variables must be non-negative to ensure they conform to physical meaning.

[0101] In practical implementation, based on the stratified characteristics of three time scales (year, month, and day), and with the objective of minimizing the water supply from lakes during the scheduling period, and in conjunction with constraints at each time scale (water balance constraints, water level limits, water demand constraints, available water constraints, pumping capacity constraints, and variable non-negativity constraints, etc.), three water optimization scheduling models are established: a first-level (annual scale) water optimization scheduling model, a second-level (monthly scale) water optimization scheduling model, and a third-level (ten-day scale) water optimization scheduling model. Specifically, the first-level model prioritizes maximizing the annual water storage of lakes to reduce the total amount of water transferred across regions. The second-level model optimizes the allocation of water resources within a ten-day period (e.g., prioritizing the use of river storage instead of lake water supply) to avoid excessive water transfer. The third-level model finely controls the daily pumping volume to further reduce the water supply.

[0102] Sub-step S202 involves combining water quantity optimization scheduling models at various time scales and constructing a three-level time scale nested water quantity optimization scheduling model through a hierarchical nested control feedback mechanism.

[0103] In the specific implementation, combined with the three-level time scale water optimization scheduling model established separately above (year, month, day), a three-level time scale nested water optimization scheduling model is finally formed through a hierarchical nested structure and a control feedback mechanism. The core logic of the control feedback mechanism is as follows: the upper level (such as the annual scale) provides the lower level (such as the monthly scale) with the lake control water level at the end of the scheduling period (as the initial condition of the lower level), the lower level provides the upper level with high-precision water inflow forecasts, and during the rolling operation of the model, the actual water resource situation at the end of the period is updated to the conditions at the beginning of the upper level's remaining period (achieving two-way information flow).

[0104] In this embodiment, by layering according to the three time scales of year, month, and day, and combining the objective function and constraints, a water optimization scheduling model is established separately for each time scale. Combining these models, a three-level nested time scale water optimization scheduling model is constructed through a layered nested control feedback mechanism. Thus, through layered nesting and the control feedback mechanism, a collaborative scheduling system that integrates long-term planning and real-time response to short- and medium-term changes is formed, effectively solving the information limitation problem of single-time-scale models.

[0105] Based on the foregoing embodiments, a third embodiment of the method for optimizing the scheduling of water volume in water diversion projects according to the present invention is proposed. In this embodiment, step S30 may include the following sub-steps S301~S303: Sub-step S301: Set the initial parameters of the improved differential evolution algorithm, and encode and constrain the decision variables of the problem in the water quantity optimization scheduling model with the three-level time scale nested structure.

[0106] The initial parameters may include the vector dimension D, the population size NP, and the total number of iterations Gmax.

[0107] The decision variables are used to represent the water supply of each river section in the lake-reservoir mixed system at each time period; specifically, they include the water supply of Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section at each time period.

[0108] As an example, taking mid-November 2015 as an example, the calculation period of the water quantity optimization scheduling model on a ten-day time scale is one ten-day period (10 days), with each period lasting one day, totaling 10 periods. Since each period corresponds to a decision variable (such as the daily water supply), the vector dimension D of the improved differential evolution algorithm is 10, the population size NP is empirically taken as 10D=100, and the total number of iterations Gmax is taken as 200 to ensure the convergence of the algorithm.

[0109] An improved differential evolution method is used to correct infeasible solutions that do not meet the constraints. Its calculation formula can be expressed as: X1=Pa(PX) (45) In the formula, P represents a feasible solution; X represents an infeasible solution; a represents the transformation coefficient, which is generally taken as 0.6~0.8; and X1 represents the corrected feasible solution.

[0110] The improved differential evolution method for handling constraints is as follows: In each generation of the population, individuals X that do not meet the constraints are selected; a feasible solution P that meets the constraints is selected from the current population; the infeasible solution X is converted into X1 using the above formula (45); if X1 still does not meet the constraints, the above steps are repeated until all infeasible solutions become feasible solutions; crossover, mutation, and selection operations are performed on all individuals (including the modified feasible solutions) to generate the next generation of the population.

[0111] In practical implementation, initial parameters for the improved differential evolution algorithm can be set, including vector dimension D, population size NP, and total number of iterations Gmax. Then, individual information encoding is performed on the decision variables in the water optimization scheduling model with a three-level time-scale nested structure. This involves encoding the decision variables onto individual gene loci according to certain rules, establishing a one-to-one encoding index. Next, the improved differential evolution method is used to handle the constraints of the three-level time-scale nested structure water optimization scheduling model. Its core is to use the difference between feasible and infeasible solutions to introduce infeasible solutions into the feasible region one by one in each generation until all infeasible solutions become feasible. Then, crossover, mutation, and selection operations are performed. Thus, by setting the initial parameters, encoding decision variables, and handling constraints in the improved differential evolution algorithm, the feasibility of the solution can be ensured, fundamentally avoiding the generation of invalid solutions.

[0112] Sub-step S302: Determine the input conditions of the water quantity optimization scheduling model with the nested structure of the three-level time scale; wherein, the input conditions include the inflow forecast, demand forecast and boundary conditions of the three-level time scale.

[0113] The three-level time scale water inflow forecast, water demand forecast, and boundary conditions are used to represent the water inflow data, water demand data, and corresponding boundary conditions for the long-term (annual), medium-term (monthly), and short-term (ten-day) time scales, respectively. For example, the three-level time scale water inflow forecast specifically includes: Long-term water inflow forecast: A water volume optimization scheduling model corresponding to an annual time scale, with a forecast period of 1 year and a forecast period of monthly (i.e., the total water inflow each month), providing a macro-level water inflow trend reference for the annual scheduling plan; Medium-term water inflow forecast: The water volume optimization scheduling model corresponds to the monthly time scale, with a forecast period of January and a forecast period of ten days (i.e., the total water inflow in each ten-day period), providing a medium-term water inflow fluctuation reference for the monthly scheduling plan; Short-term water inflow forecast: The water volume optimization scheduling model corresponds to the ten-day time scale, with a forecast period of 10 days (approximately 10 days) and a forecast period of daily (i.e., the total water inflow each day), providing real-time water inflow data support for the ten-day scheduling plan.

[0114] The same principle applies to water demand forecasts at three time scales: long-term water demand forecasts correspond to an annual scale (forecast period of 1 year, monthly time period), medium-term forecasts correspond to a monthly scale (forecast period of 1 month, ten-day time period), and short-term forecasts correspond to a ten-day scale (forecast period of 10 days, daily time period).

[0115] Boundary conditions (such as upper and lower limits of water level and storage capacity) also need to be customized according to time scale: long-term boundaries focus on annual water level changes, medium-term boundaries focus on monthly fluctuations, and short-term boundaries focus on real-time constraints on the ten-day scale.

[0116] As an example, hydrological models such as SWAT are used to forecast the daily water inflow in mid-November for the Xiangjian Lake and Sipu-Houwang River sections. See Table 2 for details, which contains water inflow data for the Xiangjian Lake and Sipu-Houwang River sections.

[0117]

[0118] Table 2. Water inflow data for Xiangjian Lake and the section from Sipu to Houwang River.

[0119] The short-term water demand forecast uses the water demand prediction results for each water-receiving area in mid-November as the water demand input. See Table 3 for details, which contains water demand data for each water-receiving area.

[0120]

[0121] Table 3 Water Demand Data for Each Water Receiving Area

[0122] Short-term boundary conditions need to clearly define the water level limits and storage constraints for each river section; specifically: Xiangjian Lake: The actual initial water level is 14.0m, and the final control water level determined by the upper-level optimization scheduling model is 14.44m, the upper limit water level is 14.67m, and the lower limit water level is 13.5m.

[0123] Lousong-Erpu section: The initial water level is 22.1m, the upper limit water level is 22.5m, the lower limit water level is 19.9m, and the storage capacity is the water volume intercepted by the upstream flood in the early stage. During the dispatching period, the water volume of Xiangjian Lake will not be used to replenish the storage capacity of this section.

[0124] The initial water level of the Sipu-Houwang section is 26.8m, the upper limit is 27m, the lower limit is 26m, and the storage capacity is the amount of water intercepted by the upstream floodwaters in the early stage. During the scheduling period, the water volume of Xiangjian Lake will not be used to supplement the storage capacity of the Sipu-Houwang section.

[0125] Please see Figure 8-10 , Figure 8-10The water level and reservoir capacity curves of Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section are displayed respectively. Figure 8 It exhibits a non-linear increasing trend, with slow growth in reservoir capacity when the water level is low and accelerated growth when the water level is high (the slope of the curve gradually increases), reflecting the influence of the topography of the lake's shallows on the reservoir capacity (for example, as the water level in the shallows rises, more volume needs to be filled, causing the reservoir capacity growth rate to accelerate as the water level rises). Figure 9 The water level increases almost linearly, and there is a strong positive correlation between water level and reservoir capacity (the slope of the curve is stable), indicating that the reservoir capacity of river-type water bodies increases uniformly with the rise in water level, and the terrain is relatively flat. Figure 10 The increase is segmented and nonlinear. When the water level is below 26.8m, the reservoir capacity increases slowly, and when it is above 26.8m, the increase accelerates. This may be related to changes in the cross-sectional shape of the river section (such as the rapid increase in reservoir capacity caused by the rise in water level in narrow and deep sections).

[0126] In the specific implementation, the input conditions of each layer of the water quantity optimization scheduling model in the three-level time scale nested structure can be determined; the input conditions specifically include the inflow forecast, water demand forecast and boundary conditions of the three-level time scale (long-term, medium-term and short-term).

[0127] Sub-step S303: Based on the inflow forecast, demand forecast, and boundary conditions of the three-level time scale, and combined with the improved differential evolution algorithm and control feedback mechanism, the water quantity optimization scheduling model of the nested structure of the three-level time scale is solved to obtain the optimized scheduling scheme.

[0128] Taking 2015 as an example, the time scale and scheduling logic of the three-layer model are as follows: The first layer (annual scale) simulates the scheduling period in 2015, with the scheduling period in January. The input is the monthly forecast of water inflow and water demand, and the output is the monthly optimized water scheduling process for each water source.

[0129] The second layer (monthly scale) simulates the scheduling period in January 2015, with scheduling time periods of 10 days (early, middle, and late ten days). The input is the inflow and demand of water for each ten-day period, and the output is the optimized water scheduling process for each water source on a ten-day basis.

[0130] The third level (ten-day scale), the scheduling simulation period: early January 2015 (January 1-10), the scheduling period is 1 day, the input is the daily forecast of water inflow and water demand, and the output is the daily optimized water scheduling process for each water source. Please refer to [link / reference]. Figure 7 , Figure 7 The solution process of a three-level time-scale nested water quantity optimization scheduling model is shown; the end-of-period water level of the upper-level model is used as the starting water level of the lower-level model; the actual water level of the lower-level model is fed back to the upper-level model for subsequent periods; and the interaction between the predicted inflow (such as the total predicted inflow for 2015) and the actual inflow of each level model is shown.

[0131] The "control" mechanism is as follows: the water level at the end of January in the first layer (annual scale) serves as the water level at the end of the scheduling period in the second layer (monthly scale), which controls the second layer model; the water level at the end of the first ten days of January in the second layer model (monthly scale) serves as the water level at the end of the scheduling period in the third layer (ten-day scale), which controls the third layer model.

[0132] Inflow "feedback" mechanism: The total inflow at the third level (ten-day scale) can replace the forecasted inflow for the first period (early January) at the second level (monthly scale). The total monthly inflow at the second level (monthly scale) can replace the forecasted inflow for the first period (January) at the first level (annual scale).

[0133] Water level "feedback" mechanism: After the third-level (ten-day scale) scheduling, the actual water level at the end of January 10th will be used as the starting water level for the second period (mid-January) of the second-level (monthly scale), adjusting the scheduling plan for the subsequent remaining period (mid-January and late January). After the second-level (monthly scale) scheduling, the actual water level at the end of January will be used as the starting water level for the second period (February) of the first-level (annual scale), adjusting the scheduling plan for the subsequent remaining period (February to December).

[0134] Following the example of sub-step S302 above, taking mid-November as the scheduling period, and relying on the improved differential evolution algorithm, combined with inflow forecasts, demand forecasts, and boundary conditions at three time scales, a ten-day time scale water quantity optimization scheduling model is solved. The solution results are the daily water transfer schemes for Xiangjian Lake, the Lousong-Erpu River section, and the Sipu-Houwang River section (i.e., the optimized scheduling schemes at the ten-day time scale). The solution results are shown in Tables 4-7, and... Figure 11 , Figure 11 The document shows the daily water supply process during mid-November 2015 (November 11 to November 20).

[0135]

[0136] Table 4 Daily Water Diversion Plan for Xiangjian Lake

[0137]

[0138] Table 5 Daily Water Diversion Plan for the Lousong-Erpu River Section

[0139]

[0140] Table 6 Daily Water Diversion Plan for the Sipu-Houwang River Section

[0141]

[0142] Table 7 Overall Water Transfer Plan for Each Water Source During the Scheduling Period

[0143] The scheduling plan obtained by solving the water volume optimization scheduling model in mid-November shows that the supply-demand ratio of each area and each time period is 100%, and the water supply fully meets the water demand. The specific structure is shown in Table 8 below.

[0144]

[0145] Table 8. Supply and Demand Analysis Results for Each Water-Receiving Area

[0146] Analysis of the scheduling results shows that during the scheduling period, the total water supply from Xiangjian Lake was 2,277,200 m³, the total water supply from the Lousong-Erpu River section was 6,477,900 m³, and the total water supply from the Sipu-Houwang River section was 1,612,700 m³. The water demand of the Xiangjian Lake-Guzhen and Guzhen-Lousong areas is entirely supplied by Xiangjian Lake. Xiangjian Lake only supplied 45,200 m³ of water to the Lousong-Erpu River section on November 11th; it did not supply water to the receiving areas upstream of Lousong Station during other periods. The water demand of the Lousong-Erpu River section and the Erpu-Sipu River section is mainly provided by the storage capacity of the Lousong-Erpu River section. The water demand of the receiving areas upstream of Sipu Station is mainly supplied jointly by the Lousong-Erpu River section and the Sipu-Houwang River section.

[0147] In summary, the optimized scheduling scheme calculated by the water quantity optimization scheduling model with a three-level time scale nested structure makes full use of local water resources and reduces the water supply of Xiangjian Lake by 8.0906 million m³ compared with the theoretical maximum water supply of Xiangjian Lake when the optimized scheduling scheme is not adopted.

[0148] In practical implementation, the inflow forecast, demand forecast, and boundary conditions of the three time scales can be input into the corresponding three-time scale nested water quantity optimization scheduling model. Based on this, combined with the improved dichotomy evolution algorithm and control feedback mechanism, the models of each layer are solved to obtain the optimized scheduling scheme of each layer model.

[0149] Furthermore, in one embodiment, sub-step S301 may include the following sub-steps A10-A30: Sub-step A10: Set the initial parameters of the improved differential evolution algorithm; wherein, the initial parameters include the vector dimension, population size and total number of iterations of the decision variables of the lake-reservoir hybrid system; the decision variables are the water supply of Xiangjian Lake, Lousong-Erpu River section and Sipu-Houwang River section at each time period; Sub-step A20: According to the real number encoding rules, the decision variables are mapped to the gene loci of the individual, a one-to-one corresponding index relationship is established, and the encoded individual is formed; Sub-step A30: For coded individuals that do not meet the boundary constraints, the difference method is used to iteratively calculate the pairing difference between feasible and infeasible solutions in the current population, and gradually correct the infeasible solutions until all of them enter the feasible region and meet the constraints.

[0150] Among them, the coded individuals are used to represent the decision variables of the optimization problem (i.e., the water supply to the corresponding water-receiving areas in Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section at each time period) mapped into the form of "chromosomes" that the algorithm can operate according to the real number encoding rules. Each individual represents a water supply scheme, and the algorithm completes the optimization by operating on the gene loci of these individuals.

[0151] Please see Figure 12 , Figure 12 This diagram illustrates the information encoding of the i-th individual in the g-th generation population; through gene loci. The one-to-one correspondence with decision variables clearly presents the encoding logic of water supply from Xiangjian Lake, Erpu-Lousong River section, and Sipu-Houwang River section to the water-receiving area at different time periods (such as the first time period and the second-D time period), which is the core carrier of individual representation in the improved differential evolution algorithm.

[0152] In the specific implementation, the initial parameters of the improved differential evolution algorithm (including the vector dimension of the decision variables, the population size, and the total number of iterations) can be set. Then, the decision variables (i.e., the water supply to the corresponding water-receiving areas in Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section at each time period) are mapped to the gene loci of individuals according to the real number encoding rules, and a one-to-one corresponding encoding index is established to form coded individuals. Subsequently, individuals that do not meet the condition constraints are selected in each generation of the population. A feasible solution that meets the condition constraints is selected from the current population. The infeasible solution is gradually corrected using the improved differential evolution algorithm (by iteratively calculating the pairing difference between feasible and infeasible solutions). If the condition constraints are still not met, the above steps are repeated until all infeasible solutions become feasible solutions. Finally, crossover, mutation, and selection operations are performed on all individuals (including the corrected feasible solutions) to generate the next generation of the population. By improving the parameter settings, real number encoding, infeasible solution correction, and evolutionary operations of the differential evolution algorithm, scientific and feasible scheduling schemes can be effectively generated, enabling large-scale optimization solutions for water supply from multiple water sources and in multiple time periods, strictly meeting engineering boundary constraints, and providing a reliable basis for water resource allocation in lake-reservoir hybrid systems.

[0153] In this embodiment, by utilizing an improved differential evolution algorithm and a control feedback mechanism, multi-timescale water quantity optimization scheduling from year to month to ten-day period is achieved. Through the transmission of water level and predicted inflow between the models at each level, the scheduling scheme is dynamically adjusted and optimized, which can better adapt to the uncertainty of water inflow and demand processes, thereby improving water resource utilization efficiency.

[0154] Based on the same inventive concept, the third embodiment of this invention also provides a water diversion project water volume optimization scheduling system corresponding to the water diversion project water volume optimization scheduling method of the foregoing embodiments. Since the problem-solving principle of the system in the third embodiment is similar to the water diversion project water volume optimization scheduling method of the foregoing embodiments, the implementation of the system can refer to the implementation of the method; repeated details will not be elaborated further. Please refer to... Figure 13 The present invention provides an optimized scheduling system for water volume in water diversion projects, the system comprising: Module 10 is defined to construct the lake and reservoir hybrid system for cross-regional water transfer in the Huaihe River North Diversion Project, and to determine the objective function and constraints of the water volume optimization scheduling model based on the principle of minimizing cross-regional water transfer volume. Module 20 is used to design a three-level time scale hierarchy of year, month and day, and adopts a hierarchical nested control feedback mechanism to build a water volume optimization scheduling model with a three-level time scale nested structure. The solution module 30 is used to solve the water quantity optimization scheduling model of the three-level time scale nested structure based on the improved differential evolution algorithm, combined with water inflow forecasts, water demand and boundary conditions at different time scales, to obtain the optimized scheduling scheme.

[0155] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for optimizing the scheduling of water volume in a water diversion project.

[0156] Figure 14 This is a schematic block diagram of the electronic device provided in an embodiment of this application. Figure 14 As shown, the electronic device includes at least one processor 401, a memory 402, at least one network interface 403, and a user interface 405. The various components in the electronic device are coupled together via a bus system 404. It is understood that the bus system 404 is used to implement communication between these components. In addition to a data bus, the bus system 404 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 14 The general will label all buses as bus systems.

[0157] The user interface 405 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0158] It is understood that memory 402 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0159] In this embodiment of the invention, the memory 402 is used to store various types of data to support the operation of the electronic device 400. Examples of this data include: any executable program for operation on the electronic device 400, such as the operating system 4021 and application programs 4022; the operating system 4021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 4022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The optimized scheduling method for water diversion projects provided in this embodiment of the invention can be included in the application program 4022.

[0160] The methods disclosed in the above embodiments of the present invention can be applied to processor 401, or implemented by processor 401. Processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 401 or by instructions in the form of software. The processor 401 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 401 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 401 may be a microprocessor or any conventional processor, etc. The steps of the water diversion project water volume optimization scheduling method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in a memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0161] In an exemplary embodiment, the electronic device 400 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to perform the aforementioned method.

[0162] In summary, this invention utilizes an improved differential evolution algorithm and a control feedback mechanism to achieve multi-timescale water quantity optimization scheduling from year to month to ten-day period, ensuring dynamic adjustment and optimization of the scheduling scheme, thereby improving water resource utilization efficiency and adapting to the uncertainties of water inflow and demand processes.

[0163] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for optimizing the scheduling of water volume in a water diversion project, characterized in that, The method includes: Construct a lake-reservoir hybrid system for inter-regional water transfer in the Huaihe River North Diversion Project, and determine the objective function and constraints of the water volume optimization scheduling model based on the principle of minimizing inter-regional water transfer volume; The design incorporates a three-tiered time scale of year, month, and ten-day period, and employs a nested control feedback mechanism to construct a water quantity optimization scheduling model with a three-tiered time scale nested structure. Based on the improved differential evolution algorithm, and combined with water inflow forecasts, water demand and boundary conditions at different time scales, the water quantity optimization scheduling model with the three-level time scale nested structure is solved to obtain the optimized scheduling scheme.

2. The method according to claim 1, characterized in that, The aforementioned lake and reservoir hybrid system for the inter-regional water transfer of the Huaihe River North Diversion Project includes: The source lakes suitable as water sources within the study area of ​​the Huaihe River North Diversion Project were identified, and the water diversion route of the Huaihe River North Diversion Project was constructed based on the hydrological and water resource conditions, water demand, and water conservancy projects within the study area. The study area includes three main regions: Bengbu District, Suzhou District, and Huaibei District. In the water diversion route, a river with a large water storage capacity is selected as the water intake reservoir, which is connected with the source lake to form a lake-reservoir hybrid system for cross-regional water diversion of the Huaihe River to the North China Water Diversion Project; wherein, the water storage capacity of the river is determined by the upper and lower limits of the river water level.

3. The method according to claim 1 or 2, characterized in that, The objective function and constraints of the water allocation optimization model, determined based on the principle of minimizing inter-regional water transfer volume, include: The objective function of the water optimization model is to minimize the water supply of the source lake during the preset scheduling period, and the constraints of the water optimization scheduling model are set. The constraints include water balance constraints, upper and lower limits of water level constraints, water demand constraints, available water constraints, pumping capacity constraints, and variable non-negativity constraints.

4. The method according to claim 1, characterized in that, The water quantity optimization scheduling model, which employs a hierarchical nested control feedback mechanism and constructs a three-level time-scale nested structure, includes: Based on the three-level time scale of year, month, and day, and in combination with the objective function and the constraints, a separate water quantity optimization scheduling model is established for each time scale. By combining water quantity optimization scheduling models at various time scales and constructing a three-level time scale nested water quantity optimization scheduling model through a hierarchical nested control feedback mechanism.

5. The method according to claim 1, characterized in that, The improved differential evolution algorithm, combined with inflow forecasts, water demand conditions, and boundary conditions at different time scales, solves the three-level nested time scale water allocation optimization model to obtain an optimized allocation scheme, including: Set the initial parameters of the improved differential evolution algorithm, and encode and constrain the decision variables of the problem-solving problem in the three-level time-scale nested water quantity optimization scheduling model; Determine the input conditions for the water quantity optimization scheduling model with the nested structure of the three-level time scale; wherein, the input conditions include inflow forecast, water demand forecast and boundary conditions of the three-level time scale; Based on the inflow forecast, demand forecast, and boundary conditions of the three time scales, and combined with the improved differential evolution algorithm and control feedback mechanism, the water quantity optimization scheduling model of the nested structure of the three time scales is solved to obtain the optimized scheduling scheme.

6. The method according to claim 5, characterized in that, The process of setting initial parameters for the improved differential evolution algorithm and encoding and constraining individual information for the decision variables in the water quantity optimization scheduling model with a three-level time scale nested structure includes: Set the initial parameters for the improved differential evolution algorithm; wherein, the initial parameters include the vector dimension of the decision variables, the population size, and the total number of iterations; the decision variables include the water supply of Xiangjian Lake, Lousong-Erpu River section, and Sipu-Houwang River section at various time periods; According to the real number encoding rules, the decision variables are mapped to the gene loci of individuals to establish a one-to-one index relationship and form an encoded individual; For coded individuals that do not meet the boundary constraints, the difference method is used to iteratively calculate the pairing difference between feasible and infeasible solutions in the current population, and gradually correct infeasible solutions until all of them enter the feasible region and meet the constraints.

7. The method according to claim 1, characterized in that, After the step of solving the water quantity optimization scheduling model with the nested structure of the three-level time scale to obtain the optimized scheduling scheme, the method further includes: Calculate the supply-demand ratio of the optimized scheduling scheme, and evaluate the optimized scheduling scheme based on the supply-demand ratio.

8. A water allocation optimization system for a water diversion project, characterized in that, The system includes: The module is used to construct the lake and reservoir hybrid system for cross-regional water transfer in the Huaihe River North Diversion Project, and to determine the objective function and constraints of the water volume optimization scheduling model with the principle of minimizing the cross-regional water transfer volume. The module is used to design a three-level time scale hierarchy of year, month, and day, and adopts a hierarchical nested control feedback mechanism to build a water volume optimization scheduling model with a three-level time scale nested structure. The solution module is used to solve the water quantity optimization scheduling model with a three-level time scale nested structure based on the improved differential evolution algorithm, combined with water inflow forecasts, water demand and boundary conditions at different time scales, to obtain the optimized scheduling scheme.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to cause the processor to perform the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed, performs the steps of the method according to any one of claims 1 to 7.

Images