Water resource optimal configuration method based on improved NSGA-II multi-objective genetic algorithm

Abstract

The invention discloses a water resource optimal configuration method based on an improved NSGA-II multi-target genetic algorithm, and the method comprises the steps: firstly, obtaining basic data and related parameters of a target drainage basin, and carrying out the reasonable generalization of the target drainage basin; secondly, analyzing a specific task of water resource optimal configuration, determining an objective function and a constraint condition of an optimal configuration model, and constructing a multi-objective water resource optimal configuration model of the watershed; then, an improved NSGA-II genetic algorithm is adopted to solve the drainage basin multi-target water resource optimal configuration model, and a Pareto non-inferior solution set is obtained; and finally, determining an optimal drainage basin water resource allocation scheme in the Pareto solution set. According to the method, efficient iteration and global optimization are realized, a high-quality solution set of a multi-target problem is effectively identified, and the requirement of autonomously selecting an optimal water resource allocation scheme is met.

Description

Technical Field

[0001] The invention belongs to the technical field of water resource allocation, and in particular relates to a water resource optimization allocation method based on an improved NSGA-II multi-objective genetic algorithm. Background Art

[0002] By adopting engineering and non-engineering measures, the scientific allocation of limited and different forms of water resources among water users is realized, which is an important scientific means to realize the scientific development and rational utilization of water resources and ensure the sustainable utilization of water resources. The multi-objective genetic algorithm greatly reduces the computational complexity by adopting a fast non-dominated sorting algorithm, and can effectively solve complex system problems. However, some intelligent optimization algorithms are prone to fall into local search or fail to obtain the optimal solution when solving high-dimensional multi-objective optimization problems. Therefore, it is worth further studying how to select a reasonable and efficient optimization algorithm or improve the optimization algorithm for solving complex multi-objective water resources optimization configuration models.

[0003] The NSGA-II algorithm is an improvement on the NSGA algorithm and has certain advantages: the fast non-dominated sorting algorithm is used to greatly reduce the computational complexity; the crowding degree and crowding degree comparison operator are used instead of the specified sharing radius, so that the individuals in the quasi-Pareto domain can be expanded to the entire Pareto domain and evenly distributed, maintaining the diversity of the population; the introduction of the elite strategy expands the sampling space, prevents the loss of the best individuals, and improves the algorithm's operation speed and anti-interference ability. However, the traditional NSGA-II algorithm still has the following problems in practical applications: (1) When initializing the population, random generation is used. Randomness means uncertainty, and the randomly generated population is uneven in the entire space, affecting the distribution of the solution set; (2) The parent individual selection method of the traditional NSGA-II algorithm is usually binary tournament selection. In terms of the tournament implementation method, the selection of the parent is close to random selection, which will affect the evolution speed of the entire population, so that the search ability of the evolutionary process cannot be guaranteed, affecting the convergence of the solution set. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a water resources optimization allocation method based on an improved NSGA-Ⅱ multi-objective genetic algorithm to achieve efficient iteration, global optimization, and effective identification of high-quality solution sets for multi-objective problems, so as to meet the requirements of autonomous selection of the best water resources allocation plan.

[0005] Technical solution: The water resources optimization allocation method based on the improved NSGA-Ⅱ multi-objective genetic algorithm of the present invention comprises the following steps:

[0006] S1. Obtain the basic data and relevant parameters of the target basin, including: basic characteristic parameters of each water transfer unit, water level-storage capacity relationship curve of water source project, and generalize the basin water resources allocation system according to the hydraulic connection between each water source and water transfer and distribution project;

[0007] S2. Analyze the specific tasks of optimizing water resources allocation, and construct a basin water resources multi-objective optimization allocation model with the minimum water shortage and the maximum ecological water supply guarantee rate of each irrigation area as the objective function, and with water balance, maximum agricultural water supply, minimum ecological water supply and non-negative variables as constraints;

[0008] S3. Use the improved NSGA-Ⅱ genetic algorithm to solve the multi-objective optimization allocation model of water resources in the basin and obtain the Pareto non-inferior solution set. Each individual in the solution set represents a water resources allocation plan for the basin.

[0009] S4. Determine the best water resources allocation plan in the Pareto solution set.

[0010] Furthermore, the multi-objective optimization configuration model of water resources in the basin constructed in S2 is:

[0011] Objective function 1: Minimize the total water shortage in the basin;

[0012]

[0013] Among them, f1(x,y) is the total water shortage in the basin, n is the total number of irrigation areas, and W xi is the agricultural water demand of the ith irrigation area; x i is the agricultural water supply in the ith irrigation area; W yi is the ecological water demand of the ith irrigation area; i is the ecological water supply of the ith irrigation area;

[0014] Objective function 2: The ecological water supply satisfaction of each irrigation area is maximized;

[0015]

[0016] Among them, f2(y) is the ecological water supply satisfaction of each irrigation area;

[0017] Constraint 1: Water balance constraint;

[0018]

[0019] Among them, W u W is the available water volume; i is the water inflow of the basin; W e The ecological base flow of the main water supply rivers;

[0020] Constraint 2: Maximum agricultural water supply constraint;

[0021] x i ≤W xi

[0022] Constraint 3: minimum ecological water demand constraint;

[0023] y i ≥αW yi

[0024] Among them, α is a parameter between 0 and 1, which is used to calculate the minimum water requirement necessary to ensure the survival of ecological vegetation;

[0025] Constraint 4: non-negative constraint;

[0026] x i ≥0;y i ≥0.

[0027] Furthermore, S3 includes the following steps:

[0028] S3-1. According to the basic situation of water resources in the basin, decision variables are selected, and each water transfer unit in the basin is divided according to the hydrological section controlled by the main water supply river. The upper and lower limits of water demand of each water transfer unit are determined, and the upper and lower bounds of the search domain of the improved NSGA-Ⅱ genetic algorithm are determined; the independent variables are the agricultural water supply and ecological water supply of each irrigation area, the number of independent variables nVar is twice the number of irrigation areas, and the maximum number of iterations t max , crossover ratio Pc, variation ratio Pm, the lower bound of the independent variable varmin is the vector data set composed of the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, the upper bound of the independent variable varmax is the vector data set composed of the maximum agricultural water supply and the maximum ecological water supply of each irrigation area, and the parent generation selection parameters ud and up;

[0029] S3-2, let the number of iterations be t = 0, and use the good point set theory to generate the initial population P0;

[0030] S3-3. Calculate the target values ​​of individuals in the population according to the objective function, that is, the total water shortage in the basin and the ecological water supply satisfaction of each irrigation area corresponding to each scheme, perform fast non-dominated sorting on the individuals and calculate the congestion degree;

[0031] S3-4, sort in ascending order according to dominance level, and then sort in descending order according to crowding distance, calculate the probability of the sorted individuals becoming parents and generate the parent population P t ;

[0032] S3-5, perform crossover and mutation operations on the parent population after the selection operation to obtain the offspring population P t+1 ;

[0033] S3-6. Check whether the genetic evolution generation has reached the maximum number of iterations. If so, terminate the operation and output the result; if not, set t=t+1 and return to S3-3 to continue.

[0034] Further, S3-2 includes the following steps:

[0035] S3-2-1. If the spatial dimension of the population is s and the population size is N, calculate the value of each point in the point set r according to the following formula:

[0036] r=(r1,r2,r3,…,r N )

[0037]

[0038] Among them, r j is a good point in the point set r, j = 1, 2, ..., N; N i represents the i-th individual in the population, i = 1, 2, ..., N;

[0039] S3-2-2. Construct a set of N good points P N (i)

[0040] P N (i) = {(r1i1, r2i2, r3i3, …, r N i N )}, i=1,2,…,N

[0041] Among them, 1≤i j ≤N, j=1,2,…,N;

[0042] S3-2-3, P N (i) Mapping to the feasible domain where the population is located:

[0043]

[0044] in, is the optimal point individual within the feasible domain, representing the water resources allocation plan; a j represents the lower limit of the current dimension, that is, the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, b j It represents the upper limit of the current dimension, that is, the maximum agricultural water supply and the maximum ecological water supply of each irrigation area.

[0045] Further, S3-4 includes the following steps:

[0046] S3-4-1. After the non-dominated sorting and crowding degree calculation, the population is first sorted in ascending order according to the dominance level, and then sorted in descending order according to the crowding distance;

[0047] S3-4-2. The N individuals in the new population obtained after sorting are x1, x2, …, x n , each individual represents a water resource allocation plan; among them, x1 is the highest ranked individual with the largest fitness value, and x n It is the lowest ranked individual with the smallest fitness value;

[0048] S3-4-3. Assume that the probability of x1 becoming a parent individual is p1, x n The probability of being a parent is p n , then the expected number of x1 after the selection operation, that is, the parent selection parameter up is:

[0049] up=N*p1

[0050] x n The expected number after the selection operation, that is, the parent selection parameter ud is:

[0051] ud=N*p n

[0052] S3-4-4. In order to make the higher ranking individuals in the parent population have a higher probability of becoming the parent, according to the arithmetic progression, the probability of the i-th individual in the population becoming the parent is:

[0053]

[0054] The sum of the expected choices of individuals in the population is N, then ud+up=2, 0≤ud≤1, up=2-ud.

[0055] The system corresponding to the method includes:

[0056] The parameter acquisition unit is used to obtain the basic information and related parameters of the target basin, including: the basic characteristic parameters of each water transfer unit, the water level-storage capacity relationship curve of the water source project, and generalize the basin water resources allocation system according to the hydraulic connection between each water source and water transfer and distribution project;

[0057] The model building unit is used to analyze the specific tasks of optimizing water resources allocation, and to build a basin water resources multi-objective optimization allocation model with the minimum water shortage and the maximum ecological water supply guarantee rate of each irrigation area as the objective function, and with water balance, maximum agricultural water supply, minimum ecological water supply and non-negative variables as constraints;

[0058] The model solving unit is used to solve the multi-objective optimization configuration model of water resources in the basin by using the improved NSGA-Ⅱ genetic algorithm to obtain the Pareto non-inferior solution set, in which each individual in the solution set represents a water resources configuration plan for the basin;

[0059] The optimal solution determination unit is used to determine the optimal basin water resources allocation solution in the Pareto solution set.

[0060] Preferably, the model solving method is:

[0061] S3-1. According to the basic situation of water resources in the basin, decision variables are selected, and each water transfer unit in the basin is divided according to the hydrological section controlled by the main water supply river. The upper and lower limits of water demand of each water transfer unit are determined, and the upper and lower bounds of the search domain of the improved NSGA-Ⅱ genetic algorithm are determined; the independent variables are the agricultural water supply and ecological water supply of each irrigation area, the number of independent variables nVar is twice the number of irrigation areas, and the maximum number of iterations t max , crossover ratio Pc, variation ratio Pm, the lower bound of the independent variable varmin is the vector data set composed of the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, the upper bound of the independent variable varmax is the vector data set composed of the maximum agricultural water supply and the maximum ecological water supply of each irrigation area, and the parent generation selection parameters ud and up;

[0062] S3-2, let the number of iterations be t = 0, and use the good point set theory to generate the initial population P0;

[0063] S3-3. Calculate the target values ​​of individuals in the population according to the objective function, that is, the total water shortage in the basin and the ecological water supply satisfaction of each irrigation area corresponding to each scheme, perform fast non-dominated sorting on the individuals and calculate the congestion degree;

[0064] S3-4, sort in ascending order according to dominance level, and then sort in descending order according to crowding distance, calculate the probability of the sorted individuals becoming parents and generate the parent population P t ;

[0065] S3-5, perform crossover and mutation operations on the parent population after the selection operation to obtain the offspring population P t+1 ;

[0066] S3-6. Check whether the genetic evolution generation has reached the maximum number of iterations. If so, terminate the operation and output the result; if not, set t=t+1 and return to S3-3 to continue.

[0067] Further preferably, S3-2 comprises the following steps:

[0068] S3-2-1. If the spatial dimension of the population is s and the population size is N, calculate the value of each point in the point set r according to the following formula:

[0069] r=(r1,r2,r3,…,r N )

[0070]

[0071] Among them, rj is a good point in the point set r, j = 1, 2, ..., N; N i represents the i-th individual in the population, i = 1, 2, ..., N;

[0072] S3-2-2. Construct a set of N good points P N (i)

[0073] P N (i) = {(r1i1, r2i2, r3i3, …, r N i N )}, i=1,2,…,N

[0074] Among them, 1≤i j ≤N, j=1,2,…,N;

[0075] S3-2-3, P N (i) Mapping to the feasible domain where the population is located:

[0076]

[0077] in, is the optimal point individual within the feasible domain, representing the water resources allocation plan; a j represents the lower limit of the current dimension, that is, the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, b j It represents the upper limit of the current dimension, that is, the maximum agricultural water supply and the maximum ecological water supply of each irrigation area.

[0078] Further preferably, S3-4 comprises the following steps:

[0079] S3-4-1. After the non-dominated sorting and crowding degree calculation, the population is first sorted in ascending order according to the dominance level, and then sorted in descending order according to the crowding distance;

[0080] S3-4-2. The N individuals in the new population obtained after sorting are x1, x2, …, x n , each individual represents a water resource allocation plan; among them, x1 is the highest ranked individual with the largest fitness value, and x n It is the lowest ranked individual with the smallest fitness value;

[0081] S3-4-3. Assume that the probability of x1 becoming a parent individual is p1, x n The probability of being a parent is p n , then the expected number of x1 after the selection operation, that is, the parent selection parameter up is:

[0082] up=N*p1

[0083] x nThe expected number after the selection operation, that is, the parent selection parameter ud is:

[0084] ud=N*p n

[0085] S3-4-4. In order to make the higher ranking individuals in the parent population have a higher probability of becoming the parent, according to the arithmetic progression, the probability of the i-th individual in the population becoming the parent is:

[0086]

[0087] The sum of the expected choices of individuals in the population is N, then ud+up=2, 0≤ud≤1, up=2-ud.

[0088] An electronic device for storing and executing the method, comprising a memory and a processor, wherein:

[0089] A memory for storing computer programs that can be run on the processor;

[0090] The processor is used to execute the steps of the water resources optimization configuration method based on the improved NSGA-Ⅱ multi-objective genetic algorithm when running the computer program.

[0091] Beneficial effects: Compared with the prior art, the significant technical effects of the present invention are as follows: (1) In view of the problem that the global search capability of the traditional NSGA-II algorithm cannot be guaranteed during the evolution process and it is easy to fall into local optimization, the optimal point set theory is introduced to generate the initial population, so that the initial population is evenly distributed and avoids falling into the local optimum; the improvement effectively improves the distribution of the solution set and improves the diversity of the population, which can further promote the application of genetic algorithms in multi-objective optimization problems; (2) In view of the high computational complexity and low efficiency of processing large-scale problems of the traditional NSGA-II algorithm, a parent selection strategy based on linear pressure is proposed, which makes the optimal The probability of the outstanding individual becoming the parent individual increases, which improves the optimization efficiency of the algorithm; the improvement effectively improves the convergence of the solution set, reduces the computational complexity, and further promotes the application of genetic algorithms in large-scale multi-objective optimization problems; (3) By systematically generalizing the target basin, a multi-objective water resources optimization allocation model for the basin is constructed, and the improved NSGA-Ⅱ genetic algorithm is used to solve the model to determine the optimal allocation plan for water resources in the basin; as an innovative method in the field of water resources optimization allocation, the present invention can provide a scientific basis for basin water resources management, provide technical support for the sustainable development of water resources, and fully guarantee the rational utilization and protection of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 is a flow chart of the method of the present invention;

[0093] Figure 2Produce a system overview diagram for the basin's water resources configuration;

[0094] Figure 3 This is the flow chart of the improved NSGA-II algorithm;

[0095] Figure 4 It is the spatial distribution diagram of the ZDT test function solution set, where (a), (b), (c), and (d) are the spatial distribution comparisons of the test functions ZDT1, ZDT2, ZDT3, and ZDT6 before and after the improvement, respectively;

[0096] Figure 5 These are the water distribution diagrams before and after the optimal allocation of water resources in the mainstream of the Tarim River. Figure (a) is a comparison of agricultural water supply allocation plans, and Figure (b) is a comparison of ecological water supply allocation plans. DETAILED DESCRIPTION

[0097] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. Various equivalent modifications of the present invention made by those skilled in the art all fall within the scope defined by the claims attached to this application.

[0098] Aiming at the defects of traditional NSGA-II algorithm in practical application, such as poor distribution of solution set, lack of guaranteed search capability and slow convergence speed, the present invention proposes a water resources optimization configuration method based on improved NSGA-Ⅱ multi-objective genetic algorithm. The method adopts the best point set strategy to initialize the population and uses the parent selection strategy based on linear pressure to adjust the elite population selection method.

[0099] like Figure 1 As shown, the water resources optimization configuration method based on the improved NSGA-Ⅱ multi-objective genetic algorithm of the present invention comprises the following steps:

[0100] S1. Obtain basic information data of the basin, including: basic characteristic parameters of each water source project (reservoir or lake), water level-storage capacity relationship curve of the water source project, and generalize the basin water resources allocation system according to the hydraulic and hydrological connection between each water source and water transmission and distribution project (water pump, sluice or water pipeline). The generalization diagram is shown in Figure 2 ;

[0101] S2. Analyze the task of water resources allocation in the basin, and construct a multi-objective optimization allocation model for water resources in the basin with the minimum water shortage and the maximum ecological water supply guarantee rate of each irrigation area as the objective function, and with water balance, maximum agricultural water supply, minimum ecological water supply, and non-negative variables as constraints:

[0102] Objective function 1: Minimize the total water shortage in the basin

[0103]

[0104] Among them, f1(x,y) is the total water shortage in the basin, n is the total number of irrigation areas, and W xi is the agricultural water demand of the ith irrigation area; x i is the agricultural water supply in the ith irrigation area; W yi is the ecological water demand of the ith irrigation area; i is the ecological water supply of the ith irrigation area;

[0105] Objective function 2: The ecological water supply satisfaction of each irrigation area is maximized

[0106]

[0107] Among them, f2(y) is the ecological water supply satisfaction of each irrigation area;

[0108] Constraint 1: Water balance constraint

[0109]

[0110] Among them, W u W is the available water volume; i is the water inflow of the basin; W e The ecological base flow of the main water supply rivers;

[0111] Constraint 2: Maximum agricultural water supply constraint

[0112] x i ≤W xi (4)

[0113] Constraint 3: Minimum ecological water demand constraint

[0114] y i ≥αW yi (5)

[0115] Among them, α is a parameter between 0 and 1, which is used to calculate the minimum water requirement necessary to ensure the survival of ecological vegetation;

[0116] Constraint 4: Non-negative constraint

[0117] x i ≥0; y i ≥0 (6)

[0118] S3. Use the improved NSGA-Ⅱ genetic algorithm to solve the basin multi-objective water resources optimization allocation model and obtain the Pareto non-inferior solution set. Each individual in the solution set represents a basin water resources allocation plan; Figure 3 As shown, the steps are as follows:

[0119] S3-1. According to the basic situation of water resources in the basin, select decision variables, divide the water transfer units in the basin according to the hydrological sections of the main water supply rivers, determine the upper and lower limits of the water demand of each water transfer unit, and determine the upper and lower bounds of the search domain of the improved NSGA-Ⅱ genetic algorithm. Define the initial population as P0, and the parent population after t iterations as P t , the offspring population is P t+1 Set the population size N, the independent variables are the agricultural water supply and ecological water supply of each irrigation area, the number of independent variables nVar is twice the number of irrigation areas, and the maximum number of iterations t max , crossover ratio Pc, variation ratio Pm, the lower bound of the independent variable varmin is the vector data set composed of the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, the upper bound of the independent variable varmax is the vector data set composed of the maximum agricultural water supply and the maximum ecological water supply of each irrigation area, and the parent generation selection parameters ud and up;

[0120] S3-2, let the number of iterations be t=0, and use the good point set theory to generate the initial population P0, which specifically includes the following steps:

[0121] S3-2-1. If the spatial dimension of the population is s and the population size is N, calculate the value of each point in the point set r according to formulas (7) to (8):

[0122] r=(r1,r2,r3,…,r N ) (7)

[0123]

[0124] Among them, r j is a good point in the point set r, j = 1, 2, ..., N; N i represents the i-th individual in the population, i = 1, 2, ..., N;

[0125] S3-2-2. Construct a set of N good points P N (i)

[0126] P N (i) = {(r1i1, r2i2, r3i3, …, r N i N )}, i=1,2,…,N (9)

[0127] Among them, 1≤i j ≤N, j=1,2,…,N;

[0128] S3-2-3, P N (i) Mapping to the feasible domain where the population is located:

[0129]

[0130] in, is the optimal point individual within the feasible domain, representing the water resources allocation plan; a j represents the lower limit of the current dimension, that is, the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, b j It represents the upper limit of the current dimension, that is, the maximum agricultural water supply and the maximum ecological water supply of each irrigation area.

[0131] S3-3, calculate the target values ​​of individuals in the population according to objective functions 1 and 2, that is, the total water shortage in the basin and the ecological water supply satisfaction of each irrigation area corresponding to each scheme, perform fast non-dominated sorting on individuals and calculate the congestion degree;

[0132] S3-4, sort in ascending order according to dominance level, and then sort in descending order according to crowding distance, calculate the probability of the sorted individuals becoming parents and generate the parent population P t , specifically including the following steps:

[0133] S3-4-1. After the non-dominated sorting and crowding degree calculation, the population is first sorted in ascending order according to the dominance level, and then sorted in descending order according to the crowding distance;

[0134] S3-4-2. The N individuals in the new population obtained after sorting are x1, x2, …, x n , each individual represents a water resource allocation scheme. Among them, x1 is the highest ranked individual with the largest fitness value, and x n It is the lowest ranked individual with the smallest fitness value;

[0135] S3-4-3. Assume that the probability of x1 becoming a parent individual is p1, x n The probability of being a parent is p n , then the expected number of x1 after the selection operation (i.e., the parent selection parameter up) is:

[0136] up=N*p1 (11)

[0137] x n The expected number after the selection operation (i.e., the parent selection parameter ud) is:

[0138] ud=N*p n (12)

[0139] S3-4-4. In order to make the higher ranking individuals in the parent population have a higher probability of becoming the parent, according to the arithmetic progression, the probability of the i-th individual in the population becoming the parent is:

[0140]

[0141] The sum of the expected choices of individuals in the population is N, then ud+up=2, 0≤ud≤1, up=2-ud.

[0142] S3-5, perform crossover and mutation operations on the parent population after the selection operation to obtain the offspring population P t+1 ;

[0143] S3-6. Check whether the number of generations of genetic evolution has reached the maximum number of iterations t max If yes, terminate the operation and output the result; if no, set t=t+1 and return to S3-3 to continue.

[0144] S4. Determine the best water resources allocation plan in the Pareto solution set.

[0145] The system corresponding to the method includes:

[0146] The parameter acquisition unit is used to obtain the basic information and related parameters of the target basin, including: the basic characteristic parameters of each water transfer unit, the water level-storage capacity relationship curve of the water source project, and generalize the basin water resources allocation system according to the hydraulic connection between each water source and water transfer and distribution project;

[0147] The model building unit is used to analyze the specific tasks of optimizing water resources allocation, and to build a basin water resources multi-objective optimization allocation model with the minimum water shortage and the maximum ecological water supply guarantee rate of each irrigation area as the objective function, and with water balance, maximum agricultural water supply, minimum ecological water supply and non-negative variables as constraints;

[0148] The model solving unit is used to solve the multi-objective optimization configuration model of water resources in the basin by using the improved NSGA-Ⅱ genetic algorithm to obtain the Pareto non-inferior solution set, in which each individual in the solution set represents a water resources configuration plan for the basin;

[0149] The optimal solution determination unit is used to determine the optimal basin water resources allocation solution in the Pareto solution set.

[0150] An electronic device for storing and executing the method, comprising a memory and a processor, wherein:

[0151] A memory for storing computer programs that can be run on the processor;

[0152] The processor is used to execute the steps of the water resources optimization configuration method based on the improved NSGA-Ⅱ multi-objective genetic algorithm when running the computer program.

[0153] Experimental verification:

[0154] The improved test results are compared with the solution results of the traditional NSGA-Ⅱ algorithm with the same parameter settings to verify the feasibility and superiority of the algorithm. Figure 4 It is a Pareto curve of the ZDT test function based on the improved and traditional NSGA-Ⅱ algorithm. Figure 4 From (a) to (d), it can be seen that for the ZDT test function, when the number of iterations is the same, the improved NSGA-Ⅱ converges faster, and the obtained solution set is closer to the known Pareto optimal solution. The improved NSGA-Ⅱ algorithm is significantly better than the traditional NSGA-Ⅱ algorithm. Taking the optimal allocation of water resources in the main stream of the Tarim River as an example, the rationality and effectiveness of the invented method are illustrated. The main stream of the Tarim River is located on the north side of the Tarim Basin. It starts at Xiaojiajie, the intersection of the Aksu River, the Yarkand River and the Hotan River, and ends at Taitema Lake. The main stream is 1,321 km long and has a drainage area of ​​17,600 km. 2 The geographical location is between 81°51'~88°30'E longitude and 39°30'~41°35'N latitude. The Tarim River is divided into three sections: upper, middle and lower reaches according to its geomorphic features. Table 1 is the actual allocation plan for the water resources of the Tarim River mainstream in 2020.

[0155] Table 1 Actual water resources allocation plan for the mainstream area of ​​the Tarim River in 2020 Unit: billion m 3

[0156]

[0157] This invention uses the agricultural water supply and ecological water supply of each irrigation area as decision variables, and uses the improved NSGA-Ⅱ algorithm for optimization configuration, achieving the total water shortage of water resources in the basin and the maximum ecological water supply guarantee rate of each irrigation area, with water balance, maximum agricultural water supply, minimum ecological water supply, non-negative constraints, etc. as constraints. The specific parameters of the improved NSGA-Ⅱ algorithm are determined as follows: population size N = 100, the number of global iterations is set to 500, and 2020 is selected for optimization configuration. The comparison of the water supply guarantee rate of the optimal configuration of water resources in the mainstream of the Tarim River in 2020 and the actual configuration scheme is shown in Figure 5 (a) and (b). Under the condition that the total regional water supply remains unchanged, compared with the actual configuration scheme, the optimization scheme improves the problem of over-supply in the Wu-A irrigation area and the A-Qia irrigation area, so that the problem of water resource waste in the region is alleviated. At the same time, the agricultural and ecological water supply guarantee rates of the A-Xin irrigation area, the Xin-Ying irrigation area, the Ying-Wu irrigation area, and the Qia-Da irrigation area are all improved. By using the improved NSGA-Ⅱ algorithm for optimization, the water shortage problem in the mainstream of the Tarim River is effectively improved, and the water supply guarantee rate of each irrigation area is improved. On the basis of making full use of the water from the Aral section, the optimization configuration scheme fully guarantees the ecological base flow and the water discharge of the Daxihaizi, so that water resources are reasonably allocated. Therefore, the set of optimal configuration schemes for water resources in the basin solved by the improved NSGA-Ⅱ algorithm is reasonable and effective.

Claims

1. A water resources optimization allocation method based on improved NSGA-Ⅱ multi-objective genetic algorithm, characterized in that: The following steps are involved: S1. Obtain the basic data and relevant parameters of the target basin, including: basic characteristic parameters of each water transfer unit, water level-storage capacity relationship curve of water source project, and generalize the basin water resources allocation system according to the hydraulic connection between each water source and water transfer and distribution project; S2. Analyze the specific tasks of optimizing water resources allocation, and construct a basin water resources multi-objective optimization allocation model with the minimum water shortage and the maximum ecological water supply guarantee rate of each irrigation area as the objective function, and with water balance, maximum agricultural water supply, minimum ecological water supply and non-negative variables as constraints; S3. Use the improved NSGA-Ⅱ genetic algorithm to solve the multi-objective optimization allocation model of water resources in the basin and obtain the Pareto non-inferior solution set. Each individual in the solution set represents a water resources allocation plan for the basin. S4. Determine the best water resources allocation plan in the Pareto solution set.

2. The water resources optimization allocation method based on the improved NSGA-Ⅱ multi-objective genetic algorithm according to claim 1 is characterized in that: The multi-objective optimization configuration model of water resources in the basin constructed in S2 is: Objective function 1: Minimize the total water shortage in the basin; Among them, f1(x,y) is the total water shortage in the basin, n is the total number of irrigation areas, and W xi is the agricultural water demand of the ith irrigation area; x i is the agricultural water supply in the ith irrigation area; W yi is the ecological water demand of the ith irrigation area; i is the ecological water supply of the ith irrigation area; Objective function 2: The ecological water supply satisfaction of each irrigation area is maximized; Among them, f2(y) is the ecological water supply satisfaction of each irrigation area; Constraint 1: Water balance constraint; Among them, W u W is the available water volume; i is the water inflow of the basin; W e The ecological base flow of the main water supply rivers; Constraint 2: Maximum agricultural water supply constraint; x i ≤W xi Constraint 3: minimum ecological water demand constraint; and i ≥αW yi Among them, α is a parameter between 0 and 1, which is used to calculate the minimum water requirement necessary to ensure the survival of ecological vegetation; Constraint 4: non-negative constraint; x i ≥0;and i ≥0。 3. The water resources optimization allocation method based on the improved NSGA-Ⅱ multi-objective genetic algorithm according to claim 1 is characterized in that: S3 includes the following steps: S3-1. According to the basic situation of water resources in the basin, decision variables are selected, and each water transfer unit in the basin is divided according to the hydrological section controlled by the main water supply river. The upper and lower limits of water demand of each water transfer unit are determined, and the upper and lower bounds of the search domain of the improved NSGA-Ⅱ genetic algorithm are determined; the independent variables are the agricultural water supply and ecological water supply of each irrigation area, the number of independent variables nVar is twice the number of irrigation areas, and the maximum number of iterations t max , crossover ratio Pc, variation ratio Pm, the lower bound of the independent variable varmin is the vector data set composed of the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, the upper bound of the independent variable varmax is the vector data set composed of the maximum agricultural water supply and the maximum ecological water supply of each irrigation area, and the parent generation selection parameters ud and up; S3-2, let the number of iterations be t = 0, and use the good point set theory to generate the initial population P0; S3-3. Calculate the target values ​​of individuals in the population according to the objective function, that is, the total water shortage in the basin and the ecological water supply satisfaction of each irrigation area corresponding to each scheme, perform fast non-dominated sorting on the individuals and calculate the congestion degree; S3-4, sort in ascending order according to dominance level, and then sort in descending order according to crowding distance, calculate the probability of the sorted individuals becoming parents and generate the parent population P t ; S3-5, perform crossover and mutation operations on the parent population after the selection operation to obtain the offspring population P t+1 ; S3-6. Check whether the genetic evolution generation has reached the maximum number of iterations. If so, terminate the operation and output the result; if not, set t=t+1 and return to S3-3 to continue.

4. The water resources optimization allocation method based on the improved NSGA-Ⅱ multi-objective genetic algorithm as claimed in claim 3 is characterized in that: S3-2 includes the following steps: S3-2-1. If the spatial dimension of the population is s and the population size is N, calculate the value of each point in the point set r according to the following formula: r＝(r1,r2,r3,…,r N ) Among them, r j is a good point in the point set r, j = 1, 2, ..., N; N i represents the i-th individual in the population, i = 1, 2, ..., N; S3-2-2. Construct a set of N good points P N (i) P N (i)={(r1i1,r2i2,r3i3,…,r N i N )},i=1,2,…,N Among them, 1≤i j ≤N, j=1,2,…,N; S3-2-3, P N (i) Mapping to the feasible domain where the population is located: in, is the optimal point individual within the feasible domain, representing the water resources allocation plan; a j represents the lower limit of the current dimension, that is, the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, b j It represents the upper limit of the current dimension, that is, the maximum agricultural water supply and the maximum ecological water supply of each irrigation area.

5. The water resources optimization allocation method based on the improved NSGA-Ⅱ multi-objective genetic algorithm as claimed in claim 3 is characterized in that: S3-4 includes the following steps: S3-4-1. After the non-dominated sorting and crowding degree calculation, the population is first sorted in ascending order according to the dominance level, and then sorted in descending order according to the crowding distance; S3-4-2. The N individuals in the new population obtained after sorting are x1, x2, …, x n , each individual represents a water resource allocation plan; among them, x1 is the highest ranked individual with the largest fitness value, and x n It is the lowest ranked individual with the smallest fitness value; S3-4-3. Assume that the probability of x1 becoming a parent individual is p1, x n The probability of being a parent is p n , then the expected number of x1 after the selection operation, that is, the parent selection parameter up is: up=N*p1 x n The expected number after the selection operation, that is, the parent selection parameter ud is: out=N*p n S3-4-4. In order to make the higher ranking individuals in the parent population have a higher probability of becoming the parent, according to the arithmetic progression, the probability of the i-th individual in the population becoming the parent is: The sum of the expected choices of individuals in the population is N, then ud+up=2, 0≤ud≤1, up=2-ud.

6. A water resources optimization allocation system based on improved NSGA-Ⅱ multi-objective genetic algorithm, characterized in that: include: The parameter acquisition unit is used to obtain the basic information and related parameters of the target basin, including: the basic characteristic parameters of each water transfer unit, the water level-storage capacity relationship curve of the water source project, and generalize the basin water resources allocation system according to the hydraulic connection between each water source and water transfer and distribution project; The model building unit is used to analyze the specific tasks of optimizing water resources allocation, and to build a basin water resources multi-objective optimization allocation model with the minimum water shortage and the maximum ecological water supply guarantee rate of each irrigation area as the objective function, and with water balance, maximum agricultural water supply, minimum ecological water supply and non-negative variables as constraints; The model solving unit is used to solve the multi-objective optimization configuration model of water resources in the basin by using the improved NSGA-Ⅱ genetic algorithm to obtain the Pareto non-inferior solution set, in which each individual in the solution set represents a water resources configuration plan for the basin; The optimal solution determination unit is used to determine the optimal basin water resources allocation solution in the Pareto solution set.

7. The water resources optimization allocation system based on the improved NSGA-Ⅱ multi-objective genetic algorithm according to claim 6 is characterized in that: The model solution method is: S3-1. According to the basic situation of water resources in the basin, decision variables are selected, and each water transfer unit in the basin is divided according to the hydrological section controlled by the main water supply river. The upper and lower limits of water demand of each water transfer unit are determined, and the upper and lower bounds of the search domain of the improved NSGA-Ⅱ genetic algorithm are determined; the independent variables are the agricultural water supply and ecological water supply of each irrigation area, the number of independent variables nVar is twice the number of irrigation areas, and the maximum number of iterations t max , crossover ratio Pc, variation ratio Pm, the lower bound of the independent variable varmin is the vector data set composed of the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, the upper bound of the independent variable varmax is the vector data set composed of the maximum agricultural water supply and the maximum ecological water supply of each irrigation area, and the parent generation selection parameters ud and up; S3-2, let the number of iterations be t = 0, and use the good point set theory to generate the initial population P0; S3-3. Calculate the target values ​​of individuals in the population according to the objective function, that is, the total water shortage in the basin and the ecological water supply satisfaction of each irrigation area corresponding to each scheme, perform fast non-dominated sorting on the individuals and calculate the congestion degree; S3-4, sort in ascending order according to dominance level, and then sort in descending order according to crowding distance, calculate the probability of the sorted individuals becoming parents and generate the parent population P t ; S3-5, perform crossover and mutation operations on the parent population after the selection operation to obtain the offspring population P t+1 ; S3-6. Check whether the genetic evolution generation has reached the maximum number of iterations. If so, terminate the operation and output the result; if not, set t=t+1 and return to S3-3 to continue.

8. The water resources optimization allocation system based on the improved NSGA-Ⅱ multi-objective genetic algorithm according to claim 7 is characterized in that: S3-2 includes the following steps: S3-2-1. If the spatial dimension of the population is s and the population size is N, calculate the value of each point in the point set r according to the following formula: r＝(r1,r2,r3,…,r N ) Among them, r j is a good point in the point set r, j = 1, 2, ..., N; N i represents the i-th individual in the population, i = 1, 2, ..., N; S3-2-2. Construct a set of N good points P N (i) P N (i)={(r1i1,r2i2,r3i3,…,r N i N )},i=1,2,…,N Among them, 1≤i j ≤N, j=1,2,…,N; S3-2-3, P N (i) Mapping to the feasible domain where the population is located: in, is the optimal point individual within the feasible domain, representing the water resources allocation plan; a j represents the lower limit of the current dimension, that is, the minimum agricultural water supply and the minimum ecological water supply of each irrigation area, b j It represents the upper limit of the current dimension, that is, the maximum agricultural water supply and the maximum ecological water supply of each irrigation area.

9. The water resources optimization allocation system based on the improved NSGA-Ⅱ multi-objective genetic algorithm according to claim 7 is characterized in that: S3-4 includes the following steps: S3-4-1. After the non-dominated sorting and crowding degree calculation, the population is first sorted in ascending order according to the dominance level, and then sorted in descending order according to the crowding distance; S3-4-2. The N individuals in the new population obtained after sorting are x1, x2, …, x n , each individual represents a water resource allocation plan; among them, x1 is the highest ranked individual with the largest fitness value, and x n It is the lowest ranked individual with the smallest fitness value; S3-4-3. Assume that the probability of x1 becoming a parent individual is p1, x n The probability of being a parent is p n , then the expected number of x1 after the selection operation, that is, the parent selection parameter up is: up=N*p1 x n The expected number after the selection operation, that is, the parent selection parameter ud is: out=N*p n S3-4-4. In order to make the higher ranking individuals in the parent population have a higher probability of becoming the parent, according to the arithmetic progression, the probability of the i-th individual in the population becoming the parent is: The sum of the expected choices of individuals in the population is N, then ud+up=2, 0≤ud≤1, up=2-ud.

10. An electronic device, characterized in that: comprising a memory and a processor, wherein: A memory for storing computer programs that can be run on the processor; A processor is used to execute the steps of the water resources optimization configuration method based on the improved NSGA-Ⅱ multi-objective genetic algorithm as described in any one of claims 1 to 5 when running the computer program.

Images