Canal system optimization water distribution method, medium, equipment and product

Abstract

The invention discloses a canal system optimization water distribution method, a medium, equipment and a product, and relates to the technical field of agricultural irrigation. The method comprises the following steps: taking the water distribution starting time, the water distribution duration and the water transmission and distribution flow of all levels of canal systems as decision variables; taking minimization of the total water shortage amount of crops in an irrigation area, the excessive irrigation water amount of the crops in the irrigation area and the water transportation and distribution loss water amount as objective functions, and taking a water diversion flow constraint, a channel water transportation capacity constraint, an irrigation time constraint and a water balance constraint as constraint conditions to construct a channel system optimization water distribution model; and solving the canal system optimization water distribution model by adopting DCNSGAIII. The model provided by the invention can adapt to dynamically changing incoming water flow and effectively process complex constraints.

Description

Technical Field

[0001] This invention relates to the field of agricultural irrigation technology, and in particular to a method, medium, equipment and product for optimizing water distribution in canal systems. Background Technology

[0002] Agricultural irrigation demands a large amount of water, but its water use efficiency is low. Inappropriate canal system allocation schemes lead to water waste and exacerbate the imbalance between water supply and demand in irrigation areas. Therefore, developing reasonable canal system water allocation schemes is of great significance for improving agricultural irrigation water use efficiency and promoting the sustainable development of irrigation areas.

[0003] With the development of information technology and artificial intelligence, optimized water allocation in irrigation canals has become an important aspect of intelligent management in agricultural irrigation districts. The main task of optimized water allocation is to scientifically determine the water allocation time and flow rate of each level of canal based on the maximum flow capacity of the canals, combined with the actual water demand of crops and the water supply situation of the irrigation district, under fixed physical characteristics of the canal system, to deliver agricultural irrigation water to farmland and meet the needs of crop growth. In recent years, research on optimized water allocation models for irrigation canals has made significant progress, with models beginning to shift from "single-objective" to "multi-objective." Current research often uses minimizing water conveyance loss, minimizing the total water shortage in the irrigation district, and minimizing the difference in water intake time among rotating irrigation groups as objective functions, combining multiple constraints such as water balance constraints and agricultural irrigation time constraints to construct canal scheduling models. Feng Tao et al. established a model with the objectives of maximizing water supply benefits for water users, minimizing the total water shortage in the irrigation district, and minimizing COD emissions in the irrigation district, thus minimizing agricultural irrigation water shortage to the greatest extent possible. Ma Jianqin et al. aimed to minimize the sum of water shortage rates during irrigation periods and the water loss in the canal system. Their results showed that compared to the empirical method, the sum of water shortage rates during irrigation periods decreased by 13.6%, and the proportion of water loss in the canal system decreased by 6.3 percentage points. Significant water resource losses occur during water distribution; therefore, accurately calculating and minimizing water loss is crucial. Current canal system optimization models are increasingly sophisticated in characterizing water loss. Li Mo et al. considered the impact of upstream canal diversion on water loss flow in their water loss calculations.

[0004] With the increasing complexity of irrigation system optimization models, intelligent optimization algorithms capable of handling multi-objective constraints have become crucial. A reasonable intelligent optimization algorithm should be able to generate scheduling schemes that meet agricultural irrigation needs through an efficient search mechanism. There are two main categories for solving irrigation models: the first is single-objective optimization algorithms, including genetic algorithms, particle swarm optimization, beetle swarm optimization, ant colony optimization, and gray wolf algorithms. The second is multi-objective optimization algorithms, such as Multiple Objective Particle Swarm Optimization (MOPSO), Non-dominated Sorting Genetic Algorithm II (NSGAII), and Non-dominated Sorting Genetic Algorithm III (NSGAIII). Xiao Mengjun used simulated annealing algorithm to optimize irrigation district water allocation, which reduced water allocation time by 1.2 days and water conveyance loss by 6.84% compared to traditional methods, thus improving water use efficiency. Lu Xiaoyue et al. established an optimized water allocation model for branch and distribution canals in irrigation districts, aiming to minimize channel water conveyance loss and the time difference in water distribution within rotating irrigation groups. They solved the model using a multi-objective particle swarm optimization algorithm. Li Jiayang et al. constructed a water allocation model with the objective functions of minimizing leakage loss and flow fluctuation in a two-stage canal system, and solved it using an improved adaptive genetic algorithm. Compared with manual methods and baseline algorithms, this algorithm improved the water utilization coefficient of the canal system. Gao Jian and Zhang Yunxin proposed a hybrid binary particle swarm optimization algorithm, which converges faster than the baseline algorithm, finding the optimal solution within approximately 12 generations, and is more efficient.

[0005] In summary, while some progress has been made in the research on canal system water distribution optimization, shortcomings remain in the following aspects. Firstly, current research often focuses on the static total water supply, neglecting the dynamic characteristics of upstream water flow. This can lead to the actual water diversion flow at the canal head potentially exceeding the inflow limit, exacerbating the imbalance between water supply and demand in agricultural irrigation areas. Secondly, existing optimization algorithms often employ penalty function methods or constraint dominance strategies to handle constrained problems. The former struggles to effectively handle complex constraints, while the latter overemphasizes feasible solutions, failing to effectively explore potential infeasible solution spaces and easily getting trapped in local optima. Summary of the Invention

[0006] The purpose of this invention is to address the imbalance between water supply and demand in irrigation districts caused by existing canal system water allocation optimization targets, and to propose a canal system optimization water allocation method, comprising the following steps: S1. Using the start time, duration, and flow rate of water distribution for all levels of canal systems as decision variables, the objective function is to minimize the total water shortage of crops in the irrigation area, the excess irrigation water for crops in the irrigation area, and the water loss from water distribution. The constraints are water diversion flow rate, canal water conveyance capacity, irrigation time, and water balance. A canal system optimization water distribution model is constructed. S2. The DCNSGAIII algorithm is used to solve the canal system optimization water distribution model.

[0007] Furthermore, the total water shortage for crops in the irrigated area is expressed as follows:

[0008]

[0009] in, U represents the total water shortage for crops in the irrigation area, and U represents the total number of main irrigation canals in the irrigation area. This represents the number of branch canals of the u-th main canal. Indicates branch canal Water demand in the irrigated area This represents the j-th branch canal of the u-th main canal. Indicates the length of a water distribution period. Indicates branch canal The flow rate of water at the end of the transmission and distribution process, Indicates branch canal Number of water transmission and distribution periods Indicates branch canal The water allocation for the irrigation area is less than the water demand of the irrigation area. Indicates branch canal The water allocation for the irrigation area is greater than or equal to the water demand of the irrigation area. Excess irrigation water for crops in an irrigation district is expressed as follows:

[0010]

[0011] in, This indicates excess irrigation water for crops in the irrigation area. Indicates branch canal The water allocation for the irrigation area is greater than the water demand of the irrigation area. Indicates branch canal The water allocation for the irrigation area is less than or equal to the water demand of the irrigation area. Water loss during transmission and distribution is expressed as follows:

[0012]

[0013]

[0014] in, This indicates the water loss during water transport and distribution in the canal system. This represents the number of the u-th main canal segment. This indicates the time when the u-th main canal begins distributing water. This indicates the water delivery and distribution time of the u-th main canal. This represents the water loss in the i-th segment of the u-th main canal during time period t. Indicates branch canal Water loss during transmission and distribution Let represent the water flow rate of the i-th segment of the u-th main canal at the end of time period t, A represent the permeability coefficient of the canal bed soil for all canals, and m represent the permeability index of the canal bed soil for all canals. This represents the length of the i-th segment of the u-th main canal. Indicates branch canal The length.

[0015] Furthermore, The water diversion flow rate constraint is:

[0016] Where U represents the total number of main canals in the irrigation district. This represents the water flow rate of the first segment of the u-th main canal at the end of time period t. This represents the water loss in the first segment of the u-th main canal during time period t. express The inflow rate of the upstream water source during the specified time period; The channel water conveyance capacity constraint is:

[0017]

[0018] in, This represents the water flow rate of the i-th segment of the u-th main canal at the end of time period t. This represents the water loss in the i-th segment of the u-th main canal during time period t. This represents the design flow rate of the i-th segment of the u-th main canal. Indicates branch canal The flow rate of water at the end of the transmission and distribution process, Indicates branch canal Water loss during transmission and distribution Indicates branch canal Design flow rate at the end; The irrigation time constraint is:

[0019]

[0020] in, This indicates the time when the u-th main canal begins distributing water. This represents the water distribution time of the u-th main canal, where T is the maximum number of water distribution periods in the irrigation district. branch canals The time to start water distribution Indicates branch canal The number of water transmission and distribution periods; The water balance constraint is:

[0021] in, This represents the water flow rate of the (i+1)th segment of the u-th main canal at the end of time period t. This represents the water loss in the (i+1)th segment of the u-th main canal during time period t. Indicates branch canal Is water being dispensed at time t? Time indicates branch canal Distribute water at time t; Time indicates branch canal No water is dispensed at time t. This represents the number of branch canals of the u-th main canal. This represents the number of the u-th main canal segment.

[0022] Furthermore, the specific steps for solving the canal system optimization water distribution model using DCNSGAIII are as follows: (1) Set the population encoding and decoding strategy and initialize the algorithm parameters; (2) Randomly initialize the parent population For the population For each water distribution scheme, the objective function and constraints are calculated. (3) Entering the iteration, the constraint boundary of the t-th iteration The offspring population changes dynamically with each iteration; it is generated through selection, crossover, and mutation operations. ; (4) For offspring populations Calculate the objective function and constraints, and compare them with the parent population. Merging to form a joint population ; (5) Based on the constraint boundary Joint population Divided into feasible solution sets and infeasible solution set ,if , for The number of solutions, where N is the population size. Perform non-dominated sorting and reference-point-based pruning strategies to select N schemes as the parent population. ;if ,Will Add all to the parent population In China, All solutions are sorted by the degree of constraint violation, and the optimal one is selected. Each solution is placed in middle; (6) Check if the maximum number of iterations has been reached. If it is, output the final Pareto optimal solution set; otherwise, return to step (3) to continue iterating.

[0023] Furthermore, the encoding strategy is as follows: The water distribution flow rate is an M-bit real number string, and the water distribution start time and water distribution duration are M-bit integer strings.

[0024] Where M represents the total number of canals in the irrigation district, and U represents the total number of main canals in the irrigation district. This represents the number of branch canals of the u-th main canal.

[0025] Furthermore, a repair strategy is adopted for the constraints on channel water conveyance capacity and irrigation time. If an individual violates the constraints, the relevant variables are adjusted to meet the constraints. The DCNSGAIII dynamic constraint handling strategy is adopted for water diversion flow constraints and water balance constraints, as detailed below:

[0026]

[0027]

[0028] in, These represent the total water shortage of crops in the irrigation area, the excess irrigation water volume for crops in the irrigation area, and the water loss during water transportation and distribution, respectively. This represents the constraint boundary of the i-th constraint in the t-th iteration. The degree of constraint violation is indicated by the following formula:

[0029]

[0030] Where q represents the number of constraints. This indicates the degree of constraint violation of x on its i-th constraint. Let x represent the constraint vector on its i-th constraint;

[0031] in, and It is a constant coefficient, and cp is a parameter that controls the decreasing trend of the dynamic constraint boundary. It is a value close to zero.

[0032] Furthermore, the non-dominated sorting and reference-point-based pruning strategies are detailed below: Given two schemes and If in the current time state, Superior The following conditions must be met: (1) It is a feasible solution. It is an infeasible solution; (2) and Both are infeasible solutions, but The degree of violation of the constraints is lower ; (3) and All are feasible solutions, but in superior Any objective function value is less than or equal to The objective function value; feasible solution set Divided into different non-dominant levels A reference-point-based pruning strategy is adopted to... Perform a truncation operation.

[0033] The present invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described canal system optimization water distribution method.

[0034] The present invention also proposes an electronic device, including a processor and a memory, wherein the processor and the memory are interconnected, the memory is used to store a computer program, the computer program includes computer-readable instructions, and the processor is configured to invoke the computer-readable instructions to execute the above-described canal system optimization water distribution method.

[0035] The present invention also proposes a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-described canal system optimization water distribution method.

[0036] The beneficial effects of the technical solution provided by this invention are: This invention constructs a multi-constraint, multi-objective canal system optimization water allocation model. The model aims to minimize the total water shortage of crops in the irrigation area, the excess irrigation water volume, and the water loss during water distribution. It achieves precise water allocation by deciding the water distribution flow rate, start time, and end time of water distribution between upstream and downstream canals. Furthermore, it introduces a water diversion flow constraint, enabling the model to more flexibly adapt to dynamic changes in incoming water, thereby improving the feasibility of the water allocation scheme. To address the challenges posed by the complex constraints in the model, this invention employs a Dynamically Constrained Non-Dominated Sorting Genetic Algorithm III (DCNSGA-III) for solution. The dynamic constraint handling strategy of DCNSGA-III guides the algorithm to traverse the infeasible solution space and reach the Pareto global optimum. Attached Figure Description

[0037] Figure 1 This is a flowchart of the canal system optimization water distribution method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the encoding strategy according to an embodiment of the present invention; Figure 3 This is an example diagram of the non-dominated sorting and reduction strategy in an embodiment of the present invention; Figure 4 This is a block diagram of an electronic device according to an exemplary embodiment of the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0039] The flowchart of the canal system optimization water distribution method of this invention is as follows: Figure 1 Specifically, it includes the following steps: S1. Using the start time, duration, and flow rate of water distribution for all levels of canal systems as decision variables, the objective function is to minimize the total water shortage of crops in the irrigation area, the excess irrigation water volume for crops in the irrigation area, and the water loss volume during water distribution. The constraints are water diversion flow rate, canal water conveyance capacity, irrigation time, and water balance. A canal system optimized water distribution model is constructed.

[0040] In the water distribution process of the canal system, water is introduced from the headworks and flows through a multi-level canal system including main canals, branch canals, distribution canals, and farm canals before finally flowing into the farmland. This invention uses a two-level canal system of main canals and branch canals as an example for modeling. Assume the irrigation district has U main canals. For the u-th main canal, it includes... Each canal section ,and branch canals As the water flows through the end of the main canal section, it is distributed to its respective branch canals, which in turn further distribute the water to their respective irrigation sub-areas. .

[0041] Preferably, the objective function of the canal system optimization water distribution model constructed in this embodiment of the invention is as follows: (1) Minimize the total water shortage of crops in the irrigation area Minimizing the water deficit for crops in the irrigation area is crucial in the formulation of canal system water allocation plans. Water shortages affect nutrient absorption and translocation, and may also lead to soil salinization, potentially causing crop yield reduction or death. This invention uses the sum of the differences between the water demand and actual water supply in the irrigation area of ​​the branch canals to represent the total water deficit for crops in the irrigation area. The specific formula is:

[0042]

[0043]

[0044] in, U represents the total water shortage for crops in the irrigation area, and U represents the total number of main irrigation canals in the irrigation area. This represents the number of branch canals of the u-th main canal. Indicates branch canal Water demand in the irrigated area This represents the j-th branch canal of the u-th main canal. Indicates the length of a water distribution period. , Indicates branch canal The flow rate of water at the end of the transmission and distribution process, Indicates branch canal Number of water transmission and distribution periods Indicates branch canal The water allocation for the irrigation area is less than the water demand of the irrigation area. Indicates branch canal When the water allocation to the irrigation area is greater than or equal to the water demand of the irrigation area, the crops in the irrigation area do not lack water and are not... Consideration is needed.

[0045] (2) Minimize excess irrigation water for crops in irrigation districts In crop irrigation, over-irrigation increases soil moisture, which may lead to poor soil aeration and affect root respiration and nutrient absorption. Furthermore, over-irrigation increases water waste and irrigation costs, and may result in excessive water use. Therefore, this invention considers excess irrigation water as a separate objective. The specific formula is:

[0046]

[0047]

[0048] in, This indicates excess irrigation water for crops in the irrigation area. Indicates branch canal The water allocation for the irrigation area is greater than the water demand of the irrigation area. Indicates branch canal When the water allocation to the irrigation area is less than or equal to the water demand of the irrigation area, there is no excess water for the crops in the irrigation area. Consideration is needed.

[0049] (3) Minimize water loss during water transmission and distribution By reducing water loss during canal distribution, this invention can cover a larger irrigated area with the same water resources, contributing to more efficient water resource utilization. Simultaneously, reducing the total amount of water loss during distribution can decrease water waste, effectively promoting the rational use and management of water resources, and is also crucial for the health and sustainable development of the entire ecosystem. This is represented as:

[0050]

[0051] This invention uses the VS-CS formula to calculate the water loss flow rate in canal systems. The specific formula is as follows:

[0052]

[0053] in, This indicates the water loss during water transport and distribution in the canal system. This represents the number of the u-th main canal segment. This indicates the time when the u-th main canal begins distributing water. This indicates the water delivery and distribution time of the u-th main canal. This represents the water loss in the i-th segment of the u-th main canal during time period t. Indicates branch canal Water loss during transmission and distribution Let represent the water flow rate of the i-th segment of the u-th main canal at the end of time period t, A represent the permeability coefficient of the canal bed soil for all canals, and m represent the permeability index of the canal bed soil for all canals. This represents the length of the i-th segment of the u-th main canal. Indicates branch canal The length.

[0054] The specific constraints of the canal system optimization water distribution model constructed in this embodiment of the invention are as follows: (1) Water diversion flow constraint During the water distribution cycle, the sum of the water diversion flows of all main canals within the irrigation district shall not exceed the inflow flow of the upstream water source. This constraint is expressed as follows:

[0055] Where U represents the total number of main canals in the irrigation district. This represents the water flow rate of the first segment of the u-th main canal at the end of time period t. This represents the water loss in the first segment of the u-th main canal during time period t. express The inflow rate of the upstream water source during a given period. By constraining the water diversion flow, the total water diversion flow of the irrigation area is ensured to adapt to dynamic changes in the inflow rate.

[0056] (2) Constraints on water conveyance capacity of channels The water flow rate of each level of channel at any given time period must not exceed its design flow rate. The constraint is expressed as follows:

[0057]

[0058] in, This represents the water flow rate of the i-th segment of the u-th main canal at the end of time period t. This represents the water loss in the i-th segment of the u-th main canal during time period t. This represents the design flow rate of the i-th segment of the u-th main canal. Indicates branch canal The flow rate of water at the end of the transmission and distribution process, Indicates branch canal Water loss during transmission and distribution Indicates branch canal Design flow rate at the terminal.

[0059] (3) Irrigation time constraints For main canals within the irrigation district, the start and end times of their water distribution must be within the irrigation district's water distribution cycle; for branch canals within the irrigation district, the start and end times of their water distribution must be within the water distribution cycle of their superior canals. The constraints are expressed as follows:

[0060]

[0061] in, This indicates the time when the u-th main canal begins distributing water. This represents the water distribution time of the u-th main canal, where T is the maximum number of water distribution periods in the irrigation district. The time to start water distribution Indicates branch canal The number of water transmission and distribution periods; (4) Water balance constraint During the entire water transmission and distribution period, the main canal section The flow rate at the end of the canal segment should be equal to that of the branch canal connected to the end of the canal segment. Water distribution flow and the next canal section The sum of the initial water distribution flow rates of the canal section:

[0062]

[0063] For the last section of the main canal Its water supply and distribution flow rate should be greater than that of the branch canals connected at the end of the canal section. Water flow rate for transmission and distribution:

[0064] in, This represents the water flow rate of the (i+1)th segment of the u-th main canal at the end of time period t. This represents the water loss in the (i+1)th segment of the u-th main canal during time period t. Indicates branch canal Is water being dispensed at time t? Time indicates branch canal Distribute water at time t; Time indicates branch canal No water is dispensed at time t. This represents the number of branch canals of the u-th main canal. This represents the number of the u-th main canal segment. express The time to start water distribution.

[0065] S2. The DCNSGAIII algorithm is used to solve the canal system optimization water distribution model.

[0066] The canal system optimization water allocation model constructed in this invention involves three optimization objectives, resulting in a high dimensionality of the objective space and increasing the complexity of the solution. NSGA-III, by introducing a reference point-based selection mechanism, can effectively guide the solution distribution of the Pareto front in the high-dimensional objective space, ensuring the diversity and uniformity of the optimization results. However, this model has many and complex constraints. When solving such complex constraint models, the constraint dominance strategy adopted by NSGAIII tends to overly favor feasible solutions, causing the population to converge to a locally feasible region and miss the global Pareto optimal solution. To overcome this difficulty, this invention adopts DCNSGAIII, which, by introducing dynamic constraint boundaries, can utilize potentially infeasible solutions during the selection process, driving the population to converge toward the global Pareto optimal solution. The main steps include: (1) Set the population encoding and decoding strategy; initialize the algorithm parameters, including: population size N, maximum number of iterations T, etc.

[0067] (2) Randomly initialize the parent population For the population For each water distribution scheme, the objective function and constraints are calculated.

[0068] (3) Entering the iteration, the constraint boundary of the t-th iteration The offspring population changes dynamically with each iteration; it is generated through selection, crossover, and mutation operations. .

[0069] (4) For offspring populations Calculate the objective function and constraints, and compare them with the parent population. Merging to form a joint population .

[0070] (5) Based on the constraint boundary Joint population Divided into feasible solution sets and infeasible solution set ,if , for The number of solutions, where N is the population size. Perform non-dominated sorting and reference-point-based pruning strategies to select N schemes as the parent population. ;if ,Will Add all to the parent population In China, All solutions are sorted by the degree of constraint violation, and the optimal one is selected. Each solution is placed in middle.

[0071] (6) Check if the maximum number of iterations has been reached. If it is, output the final Pareto optimal solution set; otherwise, return to step (3) to continue iterating.

[0072] A schematic diagram of the encoding strategy of this invention is provided. Figure 2 ,as follows: The water distribution flow rate is represented by an M-bit real number string, and the water distribution start time and duration are represented by M-bit integer strings. Under this encoding method, for the main canal u, the time period... to Inside, the head gate is opened, and the water distribution flow rate at the end of the first canal section is... At other times, the head gate of the main canal is closed, and the water flow rate of the canal is zero; for the branch canals... During the time period to Inside, the head gate of the canal is opened, and the water flow rate at the end of the canal is... At other times, the head gate is closed, and the water flow rate of the canal is zero.

[0073]

[0074] Where M represents the total number of canals in the irrigation district, and U represents the total number of main canals in the irrigation district. This represents the number of branch canals of the u-th main canal.

[0075] The canal system optimization water allocation model includes four types of constraints: canal water conveyance capacity constraint, irrigation time constraint, water diversion volume constraint, and water balance constraint. For the canal water conveyance capacity constraint and irrigation time constraint, a repair strategy is employed: if an individual violates the constraint, the relevant variables are adjusted to satisfy the constraint conditions. For example, regarding the irrigation time constraint, if the water distribution end time of the main canal... If it exceeds T, then Set as The same applies to branch canals. For water diversion flow constraints and water balance constraints, it is difficult to avoid violations by directly changing the value of a single decision variable. This invention employs the dynamic constraint processing strategy of DCNSGAIII to help the algorithm find feasible and effective water distribution schemes. Firstly, the constrained multi-objective optimization problem in this invention is expressed as follows:

[0076]

[0077]

[0078] in, These represent the total water shortage of crops in the irrigation area, the excess irrigation water volume for crops in the irrigation area, and the water loss during water transportation and distribution, respectively. This represents the constraint boundary of the i-th constraint in the t-th iteration. This indicates the degree of constraint violation. Each constraint violation value is normalized to ensure comparability between different constraints. Finally, the normalized violation values ​​of all constraints are averaged as the result. The calculation formula is as follows:

[0079]

[0080] Where q represents the number of constraints. This indicates the degree of constraint violation of x on its i-th constraint. Let x represent the constraint vector on its i-th constraint.

[0081] For a canal system water distribution scheme, as long as the constraint vector If the solution is deemed feasible under the current time condition, then it is considered feasible; otherwise, it is considered infeasible. The overall shrinkage trend is represented by the simulated annealing formula:

[0082] in, and It is a constant coefficient, and cp is a parameter that controls the decreasing trend of the dynamic constraint boundary. It is a value close to zero. ).

[0083] Because the water balance constraints and water diversion flow constraints are quite complex, if the initial constraint boundaries are set too large, the algorithm may be overly biased towards the infeasible solution region, making it difficult to converge to a feasible solution in the later stages of iteration. Therefore, this invention will... Set to 1; additionally, the final constraint boundary The constant is 0. This invention can solve for the constant using the constraint boundaries of the initial and final states. and The value of .

[0084]

[0085]

[0086] The non-dominated sorting and reference-point-based pruning strategies are as follows: According to the constraint boundary Given two schemes and If in the current time state, Superior The following conditions must be met: (1) It is a feasible solution. It is an infeasible solution; (2) and Both are infeasible solutions, but The degree of violation of the constraints is lower ; (3) and All are feasible solutions, but in superior Any objective function value is less than or equal to The objective function value; Based on the conditions mentioned above, the feasible solution set Divided into different non-dominant levels Among these, individuals belonging to lower levels have better objective function values ​​or smaller constraint violation values. In this way, both the objective and constraints can be optimized simultaneously. Subsequently, further optimization is needed... Perform a truncation operation, refer to Figure 3 Example diagram of non-dominated sorting and pruning strategies, at this time ,and Therefore, for level 1 The individual plants are pruned.

[0087] The reference-point-based pruning strategy first creates reference points on the hyperplane, then normalizes the population individuals. Next, based on the projected distances from each scheme to the reference point and the origin, the nearest reference point is assigned to each scheme. During selection, the reference point with the most associated schemes is deleted first. The core of this pruning strategy is to make the algorithm focus more on the global distribution within the target space, rather than the local density between populations, thereby improving population diversity.

[0088] In one exemplary embodiment, a computer-readable storage medium is included, which stores a computer program that, when executed by a processor, implements the aforementioned canal system optimization water distribution method.

[0089] Please see Figure 4 In one exemplary embodiment, the device further includes an electronic device including at least one processor, at least one memory, and at least one communication bus.

[0090] The memory stores a computer program, which includes computer-readable instructions. The processor calls the computer-readable instructions stored in the memory through the communication bus to execute the aforementioned canal system optimization water distribution method.

[0091] In one exemplary embodiment, a computer program product is proposed, including a computer program / instructions that, when executed by a processor, implement the steps of the aforementioned canal system optimization water distribution method.

[0092] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing water distribution in a canal system, characterized in that, Includes the following steps: S1. Using the start time, duration, and flow rate of water distribution for all levels of canal systems as decision variables, the objective function is to minimize the total water shortage of crops in the irrigation area, the excess irrigation water for crops in the irrigation area, and the water loss from water distribution. The constraints are water diversion flow rate, canal water conveyance capacity, irrigation time, and water balance. A canal system optimization water distribution model is constructed. S2. The DCNSGAIII algorithm is used to solve the canal system optimization water distribution model.

2. The method for optimizing water distribution in a canal system according to claim 1, characterized in that, The total water shortage for crops in the irrigated area is expressed as follows: in, U represents the total water shortage for crops in the irrigation area, and U represents the total number of main irrigation canals in the irrigation area. This represents the number of branch canals of the u-th main canal. Indicates branch canal Water demand in the irrigated area This represents the j-th branch canal of the u-th main canal. Indicates the length of a water distribution period. Indicates branch canal The flow rate of water at the end of the transmission and distribution process, Indicates branch canal Number of water transmission and distribution periods Indicates branch canal The water allocation for the irrigation area is less than the water demand of the irrigation area. Indicates branch canal The water allocation for the irrigation area is greater than or equal to the water demand of the irrigation area. Excess irrigation water for crops in an irrigation district is expressed as follows: in, This indicates excess irrigation water for crops in the irrigation area. Indicates branch canal The water allocation for the irrigation area is greater than the water demand of the irrigation area. Indicates branch canal The water allocation for the irrigation area is less than or equal to the water demand of the irrigation area. Water loss during transmission and distribution is expressed as follows: in, This indicates the water loss during water transport and distribution in the canal system. This represents the number of the u-th main canal segment. This indicates the time when the u-th main canal begins distributing water. This indicates the water delivery and distribution time of the u-th main canal. This represents the water loss in the i-th segment of the u-th main canal during time period t. Indicates branch canal Water loss during transmission and distribution Let represent the water flow rate of the i-th segment of the u-th main canal at the end of time period t, A represent the permeability coefficient of the canal bed soil for all canals, and m represent the permeability index of the canal bed soil for all canals. This represents the length of the i-th segment of the u-th main canal. Indicates branch canal The length.

3. The method for optimizing water distribution in a canal system according to claim 1, characterized in that, The water diversion flow rate constraint is: Where U represents the total number of main canals in the irrigation district. This represents the water flow rate of the first segment of the u-th main canal at the end of time period t. This represents the water loss in the first segment of the u-th main canal during time period t. express The inflow rate of the upstream water source during the specified time period; The channel water conveyance capacity constraint is: in, This represents the water flow rate of the i-th segment of the u-th main canal at the end of time period t. This represents the water loss in the i-th segment of the u-th main canal during time period t. This represents the design flow rate of the i-th segment of the u-th main canal. Indicates branch canal The flow rate of water at the end of the transmission and distribution process, Indicates branch canal Water loss during transmission and distribution Indicates branch canal Design flow rate at the end; The irrigation time constraint is: in, This indicates the time when the u-th main canal begins distributing water. This represents the water distribution time of the u-th main canal, where T is the maximum number of water distribution periods in the irrigation district. branch canals The time to start water distribution Indicates branch canal The number of water transmission and distribution periods; The water balance constraint is: in, This represents the water flow rate of the (i+1)th segment of the u-th main canal at the end of time period t. This represents the water loss in the (i+1)th segment of the u-th main canal during time period t. Indicates branch canal Is water being dispensed at time t? Time indicates branch canal Distribute water at time t; Time indicates branch canal No water is dispensed at time t. This represents the number of branch canals of the u-th main canal. This represents the number of the u-th main canal segment.

4. The method for optimizing water distribution in a canal system according to claim 1, characterized in that, The specific steps for solving the canal system optimization water distribution model using DCNSGAIII are as follows: (1) Set the population encoding and decoding strategy and initialize the algorithm parameters; (2) Randomly initialize the parent population For the population For each water distribution scheme, the objective function and constraints are calculated. (3) Entering the iteration, the constraint boundary of the t-th iteration The offspring population changes dynamically with each iteration; it is generated through selection, crossover, and mutation operations. ; (4) For offspring populations Calculate the objective function and constraints, and compare them with the parent population. Merging to form a joint population ; (5) Based on the constraint boundary Joint population Divided into feasible solution sets and infeasible solution set ,if , for The number of solutions, where N is the population size. Perform non-dominated sorting and reference-point-based pruning strategies to select N schemes as the parent population. ;if ,Will Add all to the parent population In China, All solutions are sorted by the degree of constraint violation, and the optimal one is selected. Each solution is placed in middle; (6) Check if the maximum number of iterations has been reached. If it is, output the final Pareto optimal solution set; otherwise, return to step (3) to continue iterating.

5. The method for optimizing water distribution in a canal system according to claim 4, characterized in that, The encoding strategy is as follows: The water distribution flow rate is an M-bit real number string, and the water distribution start time and water distribution duration are M-bit integer strings. Where M represents the total number of canals in the irrigation district, and U represents the total number of main canals in the irrigation district. This represents the number of branch canals of the u-th main canal.

6. The method for optimizing water distribution in a canal system according to claim 4, characterized in that, For constraints on channel water conveyance capacity and irrigation time, a repair strategy is adopted. If an individual violates the constraints, the relevant variables are adjusted to meet the constraints. The DCNSGAIII dynamic constraint handling strategy is adopted for water diversion flow constraints and water balance constraints, as detailed below: in, These represent the total water shortage of crops in the irrigation area, the excess irrigation water volume for crops in the irrigation area, and the water loss during water transportation and distribution, respectively. This represents the constraint boundary of the i-th constraint in the t-th iteration. The degree of constraint violation is indicated by the following formula: Where q represents the number of constraints. This indicates the degree of constraint violation of x on its i-th constraint. Let x represent the constraint vector on its i-th constraint; in, and It is a constant coefficient, and cp is a parameter that controls the decreasing trend of the dynamic constraint boundary. It is a value close to zero.

7. The method for optimizing water distribution in a canal system according to claim 6, characterized in that, The non-dominated sorting and reference-point-based pruning strategies are as follows: Given two schemes and If in the current time state, Superior The following conditions must be met: (1) It is a feasible solution. It is an infeasible solution; (2) and Both are infeasible solutions, but The degree of violation of the constraints is lower ; (3) and All are feasible solutions, but in superior Any objective function value is less than or equal to The objective function value; feasible solution set Divided into different non-dominant levels A reference-point-based pruning strategy is adopted to... Perform a truncation operation.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

9. An electronic device, characterized in that, The device includes a processor and a memory interconnected thereto, wherein the memory is used to store a computer program, the computer program including computer-readable instructions, and the processor is configured to invoke the computer-readable instructions to perform the method as described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-7.

Images