A method and device for ecological regulation of cascade reservoirs based on chaos enhanced HHO

Abstract

The present application belongs to the field of ecological environment technology, and specifically discloses a method and device for ecological scheduling of cascade reservoirs based on chaos enhanced HHO. In the present application, an initial population is generated based on a chaos strategy in the search space, and then the position of each individual is updated according to the fitness of each individual, and the global optimal individual position and the historical extreme individual position are updated. According to the escape energy, different search strategies are selected to update the position of each individual. Finally, when it is determined that the number of fitness evaluations reaches the maximum number of evaluations, the updated global optimal individual position is obtained according to each updated individual position. Thus, the chaotic strategy is introduced into the Harris Eagle algorithm, which effectively overcomes the problems of reduced individual diversity and low convergence accuracy of the original HHO in solving the ecological problems of cascade reservoirs, increases the diversity of generated individuals, and improves the convergence accuracy of the algorithm.

Description

Technical Field

[0001] The present application belongs to the field of ecological environment technology, and more specifically, relates to a method and device for ecological dispatching of cascade reservoirs based on chaos enhanced HHO. Background Art

[0002] Reservoirs are built on rivers or other water bodies to intercept and store water resources, thereby significantly improving the efficiency of water resource utilization. However, during the operation of reservoirs, the hydrological conditions of rivers are affected by changes in the size, frequency and duration of outflow. At present, the scheduling and operation mode of reservoirs mainly maximizes the power generation benefits by adjusting the water level process. In order to control the safe and stable operation of reservoirs, outflows are often adjusted, resulting in significant changes in the water volume of downstream rivers compared with before the construction of reservoirs, which has a serious impact on river ecosystems and has serious negative effects on the ecological environment. In recent years, with the increasing awareness of environmental protection, research and attention on reducing or eliminating the adverse effects of reservoirs on river health have increased worldwide. Therefore, the reservoir operation mode that considers the natural river flow conditions (i.e., ecological needs) has become a hot topic in current research. It aims to balance the relationship between the economic benefits of reservoirs and ecological and environmental protection through more scientific and reasonable scheduling strategies, and ensure the sustainable use of water resources and the health and stability of river ecosystems.

[0003] Existing reservoir management usually involves the joint operation and collaboration of cascade reservoirs, which is a typical complex multi-stage decision-making problem with multiple constraints and spatiotemporal coupling characteristics. The methods for solving such problems can be mainly summarized into two categories: the first category is traditional mathematical programming methods, including nonlinear programming, linear programming, and dynamic programming. These methods usually require that the optimization problem has clear mathematical expressions and constraints, and these conditions often need to meet certain requirements, such as concavity and continuity. However, in the operation and scheduling problems of cascade reservoirs, many constraints are difficult to describe with precise mathematical models, which increases the difficulty of solving the problem. The second category is the heuristic optimization method that has emerged in recent years. This type of method does not depend on the specific form of the problem, but handles various types of optimization problems by simulating natural processes or human intelligent behavior. However, heuristic algorithms are prone to fall into local optimal solutions during the search process, and it is difficult to effectively balance the relationship between exploration and utilization, which brings challenges in practical applications. Therefore, it is of great significance to develop an algorithm with strong search ability and high convergence accuracy to find a sustainable scheduling solution for cascade reservoirs. The developed algorithm needs to be able to handle complex constraints and avoid falling into local optimality during the search process, while ensuring that the global optimal solution or a solution close to the global optimal solution is found.

[0004] In recent years, heuristic algorithms have been designed and applied to many reservoir operation problems due to their high efficiency and easy implementation, and have become a powerful solution technology. Since its proposal, Harris Hawks Optimization (HHO) has attracted widespread attention from researchers in various fields, and has been successfully applied to tasks such as feature selection, image segmentation, and vehicle path planning. Although HHO shows good search performance, it still has certain limitations in the application of cascade reservoir ecological operation. For example, the random generation of the initial population is affected by the hardware conditions of the equipment, and it is difficult to ensure population diversity. In addition, in multiple local optimal optimization problems, there is an imbalance between exploration and utilization. These shortcomings prevent the algorithm from accurately locating the global optimal position or cause the search to stagnate. Therefore, research and development of improved HHO-based algorithms are of great significance for enhancing reservoir operation. Summary of the invention

[0005] In view of the defects of the prior art, the purpose of this application is to provide a method and device for ecological scheduling of cascade reservoirs based on chaos enhanced HHO, aiming to solve the problems of reduced individual diversity and low convergence accuracy of the original HHO in the prior art in solving ecological problems of cascade reservoirs.

[0006] To achieve the above objectives, in a first aspect, the present application provides a cascade reservoir ecological dispatching method based on chaos enhanced HHO, comprising:

[0007] Determine the input parameters of the chaos enhanced Harris Hawk algorithm, the input parameters at least include the maximum number of evaluations;

[0008] Based on the chaotic strategy, an initial population is generated in the search space, and the individuals in the initial population correspond to the decision variables in the ecological operation scheme of the cascade reservoirs.

[0009] According to the fitness of each individual, the position of each individual is updated;

[0010] According to the fitness of each individual, update the global optimal individual position and the historical extreme individual position;

[0011] Select different search strategies based on the escape energy and update each individual position;

[0012] When the number of fitness evaluations of each individual based on the fitness of each individual is less than the maximum number of evaluations, return to execute updating of each individual position according to the fitness of each individual until the number of fitness evaluations reaches the maximum number of evaluations, and when the number of fitness evaluations reaches the maximum number of evaluations, determine the updated global optimal individual position according to each individual position after the update;

[0013] According to the updated global optimal individual position, the optimal ecological scheduling plan of cascade reservoirs is determined.

[0014] In some embodiments, generating an initial population in the search space based on a chaotic strategy includes:

[0015] Randomly generate N individual positions in the search space based on the chaotic strategy;

[0016] The N individual positions are determined as the initial population.

[0017] In some embodiments, the position of each individual is updated according to the fitness of each individual, including:

[0018] For any individual:

[0019] The individual position is updated according to the relationship between the individual fitness in the current fitness evaluation process and the individual fitness in the next fitness evaluation process.

[0020] In some embodiments, according to the fitness of each individual, updating the global optimal individual position and the historical extreme individual position includes:

[0021] Update the global optimal individual position according to the individual position corresponding to the minimum fitness among all individual fitnesses;

[0022] For any individual, the historical extreme individual position is updated according to the individual position with the minimum fitness obtained during the individual fitness evaluation process.

[0023] In some embodiments, different search strategies are selected based on the escape energy to update each individual position, including:

[0024] When the absolute value of the escape energy is greater than or equal to 1, the individual exploration strategy is executed to update the position of each individual;

[0025] When the absolute value of the escape energy is less than 1, the individual utilization strategy is executed to update the position of each individual;

[0026] Execute the random mutation strategy and update each individual position after the update.

[0027] In some embodiments, updating each individual position based on the escape energy includes:

[0028] When the absolute value of the escape energy is greater than or equal to 1, the individual exploration strategy is executed to update the position of each individual;

[0029] When the absolute value of the escape energy is less than 1, the individual utilization strategy is executed to update the position of each individual;

[0030] Execute the random mutation strategy and update each individual position after the update.

[0031] In some embodiments, when the absolute value of the escape energy is greater than or equal to 1, an individual exploration strategy is executed to update each individual position, including:

[0032] For any individual:

[0033] The individual balance factor is used to adaptively adjust the search step size during the individual exploration process to update the individual position;

[0034] Accordingly, when the absolute value of the escape energy is less than 1, the individual utilization strategy is executed to update the position of each individual, including:

[0035] For any individual:

[0036] Random numbers and the absolute value of the escape energy are used to select individuals for dive search or attack search behavior to update the individual position.

[0037] In some embodiments, a random mutation strategy is executed to update each updated individual position again, including:

[0038] For any individual:

[0039] A random mutation strategy is executed to generate a mutated individual position corresponding to the updated individual position, and based on the crossover probability, the position vector of any dimension in the updated individual position is replaced to update each updated individual position again.

[0040] In the second aspect, the present application provides a cascade reservoir ecological dispatching device based on chaos enhanced HHO, comprising:

[0041] An acquisition module is used to determine input parameters of the chaos enhanced Harris Hawk algorithm, and the input parameters at least include a maximum number of evaluations;

[0042] The first generation module is used to generate an initial population based on a chaotic strategy in the search space, and the individuals in the initial population correspond to the decision variables in the ecological dispatching scheme constituting the cascade reservoirs;

[0043] The first updating module is used to update the position of each individual according to the fitness of each individual;

[0044] The second updating module is used to update the global optimal individual position and the historical extreme individual position according to the fitness of each individual;

[0045] The third updating module is used to select different search strategies based on the escape energy and update each individual position;

[0046] A processing module, used for returning to execute updating of each individual position according to the fitness of each individual, when the number of fitness evaluations of each individual based on the fitness of each individual is less than the maximum evaluation number, until the number of fitness evaluations reaches the maximum evaluation number, and determining the updated global optimal individual position according to each individual position after the fitness evaluation reaches the maximum evaluation number;

[0047] The second generation module is used to determine the optimal ecological scheduling plan of the cascade reservoirs according to the updated global optimal individual positions.

[0048] In a third aspect, the present application provides an electronic device, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the cascade reservoir ecological scheduling method based on chaos enhanced HHO described in the first aspect or any embodiments of the first aspect.

[0049] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the cascade reservoir ecological scheduling method based on chaos enhanced HHO described in the first aspect or any possible implementation of the first aspect.

[0050] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0051] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0052] The present application provides a method and device for ecological dispatching of cascade reservoirs based on chaos-enhanced HHO, which generates an initial population based on a chaos strategy in the search space, and then updates the position of each individual according to the fitness of each individual, and updates the global optimal individual position and the historical extreme individual position. According to the escape energy, different search strategies are selected to update the position of each individual, and finally, when it is determined that the number of fitness evaluations reaches the maximum number of evaluations, the updated global optimal individual position is obtained according to the updated position of each individual. Thus, the introduction of chaos strategy in the Harris Eagle algorithm effectively overcomes the problems of reduced individual diversity and low convergence accuracy of the original HHO in solving ecological problems of cascade reservoirs, increases the diversity of generated individuals, and improves the convergence accuracy of the algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1It is one of the flow diagrams of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application;

[0054] Figure 2 This is the second flow chart of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application;

[0055] Figure 3 It is a box-type schematic diagram of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application at a frequency of 25% Laishui;

[0056] Figure 4 It is a box-type schematic diagram of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application at a water inflow frequency of 50%;

[0057] Figure 5 It is a box-type schematic diagram of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application at a water inflow frequency of 75%;

[0058] Figure 6 It is a schematic diagram of the convergence process of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in an embodiment of the present application under 25% frequency of water inflow;

[0059] Figure 7 It is a schematic diagram of the convergence process of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in an embodiment of the present application under 50% frequency of water inflow;

[0060] Figure 8 It is a schematic diagram of the convergence process of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in an embodiment of the present application under 75% frequency of water inflow;

[0061] Fig. 9 It is a structural schematic diagram of a cascade reservoir ecological dispatching device based on chaos enhanced HHO provided in an embodiment of the present application;

[0062] Fig.10 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0065] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of objects. For example, a first generation module and a second generation module are used to distinguish different generation modules rather than to describe a specific order of generation modules.

[0066] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0067] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more than two. The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0068] In view of the defects of the prior art, the purpose of this application is to solve the technical problems of Harris Eagle algorithm in solving ecological problems of cascade reservoirs, such as reduced individual diversity, low convergence accuracy and unbalanced exploration and development processes. The specific implementation is as follows.

[0069] See also Figure 1 The cascade reservoir ecological scheduling method based on chaos enhanced HHO provided in the embodiment of the present application may include: steps 110 to 170.

[0070] Step 110 determines input parameters of the chaos enhanced Harris Hawk algorithm, the input parameters at least including a maximum number of evaluations;

[0071] Step 120 generates an initial population based on a chaotic strategy in the search space, where individuals in the initial population correspond to decision variables in the ecological dispatching scheme constituting the cascade reservoirs;

[0072] Step 130 updates the position of each individual according to the fitness of each individual;

[0073] Step 140 updates the global optimal individual position and the historical extreme individual position according to the fitness of each individual;

[0074] Step 150 selects different search strategies based on the escape energy and updates each individual position;

[0075] Step 160: when the number of fitness evaluations for each individual based on the fitness of each individual is less than the maximum number of evaluations, return to execute updating the position of each individual according to the fitness of each individual until the number of fitness evaluations reaches the maximum number of evaluations, and when the number of fitness evaluations reaches the maximum number of evaluations, determine the updated global optimal individual position according to each individual position after the update;

[0076] Step 170 determines the optimal ecological scheduling scheme for the cascade reservoirs based on the updated global optimal individual positions.

[0077] Please see further Figure 2 Before step 110, the method may further include calculating the ecological flow rate of the ecological control section of the selected cascade reservoirs, specifically:

[0078] Select ecological control sections, collect long series of river channel restoration flow data and calculate the ecological flow of natural conditions. The ecological flow calculation method is expressed as follows:

[0079]

[0080] Among them, Fn a is the vector of natural flow of the ath ecological control section (i.e. ecological flow), with a time period of months and a total period of years; n is the number of samples with a year as the cycle; Y n is the total number of years; NF b is the vector of ecological flow in year b.

[0081] Set the input parameters of the Chaos Enhanced Harris Hawk Algorithm (CEHHO), where the input parameters are specifically described as the initial escape energy E0, the crossover probability cr, the number of individuals in the population N, the maximum number of evaluations K, and the maximum number of repeated runs of the algorithm R e .

[0082] Initial population generation: using a chaotic strategy to generate an initial population in the search space corresponding to the population, wherein the initial population is an N×D real-valued matrix, and D represents the dimension of the problem to be solved. In the embodiment of the present application, the problem to be solved is to optimize the ecological scheduling scheme of the cascade reservoirs. The individuals in the initial population correspond to the decision variables in the ecological scheduling scheme of the cascade reservoirs, and the dimensions correspond to the values ​​of the decision variables in the ecological scheduling scheme. The decision variable can be specifically any one of the water level of the reservoir in a certain period of time, the operating water level of the power station in a certain period of time, and the outflow flow of the power station in a certain period of time. Assuming that there are two values ​​of the water level in a certain period of time, the dimension is 2.

[0083] Individual fitness evaluation and position update. After evaluating the fitness of each individual position in the current generation population, the individual position is further updated. Among them, the fitness evaluation is to substitute each individual position in the population (including the individual position vector in different dimensions) into the fitness function to calculate the fitness of each individual.

[0084] In the embodiment of the present application, the fitness function F can be obtained according to the difference between the vector of the natural flow of the ecological control section and the reservoir control flow state, and the specific expression is as follows:

[0085]

[0086] Among them, Fn a and Fo a They represent the flow sequence of the natural flow state of the river in the ath ecological control section (i.e., the vector of the natural flow state) and the flow sequence after the reservoir is built (i.e., the reservoir-controlled flow state); dist[·] represents Fn a with Fo a T represents the number of time periods in the scheduling cycle, c represents the cascade reservoirs, and l represents the number of cascade reservoirs.

[0087] The global optimal position and the historical extreme individual position are updated. Specifically, according to the fitness of each individual in the population, the global optimal individual position and the historical extreme individual position in the current population are updated. Among them, the global optimal individual position is the individual position with the smallest fitness among the fitness of all individuals in the current population iteration process. For any individual, the historical extreme individual position is the individual position with the smallest fitness obtained by the individual in the evolution process.

[0088] Different search strategies (such as individual exploration strategy and individual utilization strategy) are selected according to the calculated escape energy, and the position of each individual is updated.

[0089] Record the current number of evaluations and determine whether the maximum number of evaluations has been reached. If reached, output the global optimal individual position as the optimal ecological scheduling plan for the cascade reservoirs. Otherwise, return to execute and update each individual position according to the fitness of each individual for repeated iterative calculations until the maximum number of evaluations is reached.

[0090] The above are all the steps for the algorithm to execute once. The number of times the algorithm is repeated is recorded and it is determined whether the maximum number of repeated runs is reached. If not, it returns to execute in the search space based on the chaotic strategy, generates the initial population for repeated iterations until the maximum number of repeated runs is reached.

[0091] In the embodiment of the present application, R can also be repeatedly run according to the algorithm. eAfterwards, based on the global optimal individual position output each time and combined with actual needs, a most suitable global optimal individual position is selected as the optimal ecological scheduling plan for the cascade reservoirs.

[0092] The method for ecological dispatching of cascade reservoirs based on chaos-enhanced HHO provided in the embodiment of the present application generates an initial population based on a chaos strategy in the search space, and then updates the position of each individual according to the fitness of each individual, and updates the global optimal individual position and the historical extreme individual position. According to the escape energy, different search strategies are selected to update the position of each individual. Finally, when it is determined that the number of fitness evaluations reaches the maximum number of evaluations, the updated global optimal individual position is obtained according to the updated position of each individual. Thus, the introduction of chaos strategy in the Harris Eagle algorithm effectively overcomes the problems of reduced individual diversity and low convergence accuracy of the original HHO in solving the ecological problems of cascade reservoirs, increases the diversity of generated individuals, and improves the convergence accuracy of the algorithm.

[0093] Furthermore, in some embodiments, in step 120, generating an initial population in the search space based on a chaotic strategy may include:

[0094] Randomly generate N individual positions in the search space based on the chaotic strategy;

[0095] The N individual positions are determined as the initial population.

[0096] In the specific implementation, N individual positions are generated based on the chaotic strategy, and these N individual positions are used as the initial population.

[0097] For the i-th (can be any one) individual position X i , its specific manifestations are as follows:

[0098] X i =Lb·(Lb+χ·(Ub-Lb);

[0099] χ=(χ1,...,χ j ,...,χ D );

[0100]

[0101] Where i = 1, 2, ..., N, Lb and Ub represent the upper and lower boundaries of the search space, i.e., the upper and lower boundaries of the decision variables in the problem that individuals in the population can search for, D represents the dimension of the individual position, χ1 and are uniformly distributed random numbers in the interval [0,1].

[0102] Furthermore, in some embodiments, in step 130, updating the position of each individual according to the fitness of each individual may include:

[0103] For any individual:

[0104] The individual position is updated according to the relationship between the individual fitness in the current fitness evaluation process and the individual fitness in the next fitness evaluation process.

[0105] In the specific implementation, for any individual: Assuming the position of the i-th individual, the update method of the i-th individual position based on the fitness of the individual is expressed as follows:

[0106]

[0107] Among them, X i (k+1) represents the position of the i-th individual in the k+1th fitness evaluation process, X i (k) represents the position of the i-th individual in the k-th fitness evaluation process, F(X i (k+1)) represents the fitness of the i-th individual in the k+1th fitness evaluation process, F(X i (k)) represents the fitness of the i-th individual in the k-th fitness evaluation process. In the embodiment of the present application, k represents the current fitness evaluation number, and k+1 represents the next fitness evaluation number.

[0108] Further, in some embodiments, in step 140, updating the global optimal individual position and the historical extreme individual position according to the fitness of each individual may include:

[0109] Update the global optimal individual position according to the individual position corresponding to the minimum fitness among all individual fitnesses;

[0110] For any individual, the historical extreme individual position is updated according to the individual position with the minimum fitness obtained during the individual fitness evaluation process.

[0111] In the specific implementation, the individual position corresponding to the minimum fitness among all individual fitness is taken as the global optimal position, and the individual position with the minimum fitness obtained in the individual evolution process (i.e., fitness evaluation process) is taken as the historical extreme individual position, which is specifically expressed as follows:

[0112]

[0113] In the formula, X prey (k) is the global optimal individual position in the current population during the kth fitness evaluation process, P i (k) is the historical extreme individual position corresponding to the i-th individual during the k-th fitness evaluation.

[0114] Further, in some embodiments, in step 150, updating each individual position based on the escape energy may include:

[0115] When the absolute value of the escape energy is greater than or equal to 1, the individual exploration strategy is executed to update the position of each individual;

[0116] When the absolute value of the escape energy is less than 1, the individual utilization strategy is executed to update the position of each individual;

[0117] Execute the random mutation strategy and update each individual position after the update.

[0118] Please continue to see Figure 2 , step 140 can be specifically regarded as a search strategy selection. According to the currently obtained escape energy E (|E| is used in the embodiment of the present application), a population individual is selected to explore or utilize a method to generate a new individual position, specifically:

[0119] When |E| is greater than or equal to 1, the individual exploration strategy is executed to update the position of each individual.

[0120] When |E| is less than 1, the individual utilization strategy is executed and the position of each individual is updated.

[0121] Among them, the individual exploration strategy is: use the balance factor η of any individual in the current population to adaptively adjust the search step size during the individual exploration process and generate a new individual position. The individual utilization strategy is: use the random number r and the absolute value of the escape energy |E| to select individuals for dive search or attack search behavior.

[0122] Execute the random mutation strategy and update each individual position after the update.

[0123] Furthermore, in one embodiment, when the absolute value of the escape energy is greater than or equal to 1, in the above steps, executing the individual exploration strategy and updating each individual position may include:

[0124] For any individual:

[0125] The individual balance factor is used to adaptively adjust the search step size during the individual exploration process to update the individual position;

[0126] Accordingly, when the absolute value of the escape energy is less than 1, the individual utilization strategy is executed to update the position of each individual, including:

[0127] For any individual:

[0128] Random numbers and the absolute value of the escape energy are used to select individuals for dive search or attack search behavior to update the individual position.

[0129] In the specific implementation, the balance factor η of any individual in the current population is expressed as follows:

[0130]

[0131] Among them, max[F(X(k))] represents the maximum fitness of individuals in the population during the kth fitness evaluation process. The balance factor η is used to adaptively adjust the search step size during the individual exploration process and generate new individual positions to update the individual positions, which can be specifically expressed as follows:

[0132]

[0133] In the formula, A1(k) and A2(k) represent the temporary individual position corresponding to the i-th individual position generated in the k-th fitness evaluation process, r1 and r2 represent random numbers uniformly distributed in the interval [0,1], and X rand (k) represents the position of the individual randomly selected during the kth fitness evaluation process, and E is the escape energy during the kth fitness evaluation process, which is calculated as follows:

[0134]

[0135] Where k is the number of fitness evaluations of the current population.

[0136] The random number r and the absolute value of the escape energy are used to select individuals for dive search or attack search behavior. Among them, the attack search behavior can be expressed as follows:

[0137]

[0138] X i (k+1)=X prey (k)-E|ΔX(k)|,ifr≥0.5and|E|<0.5;

[0139] Where r5 represents a random number uniformly distributed in the interval [0,1], ΔX(k) represents the difference between the position of the individual with the minimum fitness and the position of each individual in the current population, and J represents the jump intensity of the prey (i.e., the position of the individual with the minimum fitness) during the random escape process in each iteration.

[0140] The dive search behavior can be expressed as follows:

[0141] If r<0.5 and |E|≥0.5:

[0142] Y=X prey(k)-E|J·X prey (k)-X i (k)|;

[0143] Z = Y + S × Lf (D);

[0144]

[0145]

[0146] Wherein, Y and Z respectively represent the temporary individual position corresponding to the i-th individual position in the k-th fitness evaluation process, F(Y) represents the fitness of the temporary individual position Y corresponding to the i-th individual position in the k-th fitness evaluation process, F(Z) represents the fitness of the temporary individual position Z corresponding to the i-th individual position in the k-th fitness evaluation process, u and v are both random numbers uniformly distributed in the interval [0,1], β is a constant term, which is taken as 1.5 in the embodiment of the present application, Γ is a gamma function, S is a randomly generated 1×D position bit quantity, and Lf is a random number generated by Levy distribution.

[0147] If r<0.5 and |E|≥0.5:

[0148]

[0149]

[0150] Among them, X m (k) is the mean of all individual positions during the kth fitness evaluation process.

[0151] The method for ecological scheduling of cascade reservoirs based on chaos-enhanced HHO provided in the embodiment of the present application increases the diversity of generated individuals and improves the convergence efficiency and accuracy of the algorithm by selecting an individual exploration strategy or an individual utilization strategy based on the current escape energy obtained to update the individual position, and updates the updated individual position again based on a random mutation strategy, thereby effectively balancing the imbalance between the exploration and development processes of HHO in solving ecological problems of cascade reservoirs.

[0152] Furthermore, in some embodiments, in the above steps, executing the random mutation strategy to update each updated individual position again may include:

[0153] For any individual:

[0154] A random mutation strategy is executed to generate a mutated individual position corresponding to the updated individual position, and based on the crossover probability, the position vector of any dimension in the updated individual position is replaced to update each updated individual position again.

[0155] In the specific implementation, for any individual, the updated individual position is updated again by executing the random mutation strategy. More specifically, the updated individual position is subjected to the random mutation strategy to generate the mutated individual position, and the individual's dimensional position is replaced according to the crossover probability cr. The random difference mutation strategy is expressed as follows:

[0156]

[0157]

[0158] Among them, B ij (k) represents the position vector of the mutated individual position corresponding to the i-th individual position in the k-th fitness evaluation process in the j-th dimension, X ij (k) represents the position vector of the i-th individual position in the j-th dimension during the k-th fitness evaluation process, r6 and r7 represent random numbers uniformly distributed in the interval [0,1], and X rand1 (k), X rand2 (k) and X rand3 (k) represents the three individual positions randomly selected during the kth fitness evaluation process, randi(D) represents a random number randomly selected from D, and F(B i (k)) represents the fitness of the mutant individual corresponding to the i-th individual position in the k-th fitness evaluation process, B i (k) represents the mutated individual position corresponding to the i-th individual position during the k-th fitness evaluation process.

[0159] In order to verify the effect of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application, a case study used four cascade reservoirs in a certain basin as the research objects, in which the downstream of the last level of the cascade reservoir was used as the ecological control section, and relevant data were collected for simulation experiments. The established ecological dispatching model is as follows:

[0160] 1) Fitness function evaluation:

[0161] Reservoir construction often destroys the integrity and function of the basin ecosystem. The natural flow state is considered to be the optimal state of the ecosystem for reservoir operation. In order to more accurately evaluate hydrological changes, the dynamic time warping (DTW) method is used to measure the difference between the current reservoir operation and the natural flow system. The optimization goal is to minimize the change in the hydrological situation of the key control section of the reservoir, and the expression is as follows:

[0162]

[0163] Among them, Fo a It is related to the values ​​of decision variables in the ecological scheduling plan.

[0164] Exemplarily, the constraints followed by the decision variables may include:

[0165] 1) Water balance constraints:

[0166]

[0167] Among them, V c,t′+1 represents the water level of the cth cascade reservoir at the t′+1 period, V c,t′ , O i,t and q c,t′ The inflow, outflow and interval flow of the cth cascade reservoir at the t′ period, O d,t′ is the outflow from the upstream reservoir d that has direct hydraulic connection with the cth cascade reservoir at the t′th period; U c represents the number of upstream reservoirs that have direct hydraulic connection with the cth cascade reservoir, Δ t′ Represents the time interval between t′ and t′+1.

[0168] 2) Operation water level constraints:

[0169]

[0170] in, and are the minimum and maximum operating water levels of the i′th power station in the t′th period, respectively. i′,t It represents the operating water level of the i′th power station in the t′th period.

[0171] 3) Outbound flow constraints:

[0172]

[0173] in, and are the minimum outflow and maximum outflow of the i′th power station in the t′th period, respectively. i′,t′ is the outflow flow of the i′th power station in the t′th period.

[0174] 4) Constraints on outflow water balance:

[0175]

[0176] Among them, s i′,t′ and are the abandoned water volume and power generation flow of the i′th power station in the t′th period respectively.

[0177] 5) Power station output constraints:

[0178]

[0179] in, and are the minimum and maximum output of the i′th power station in the t′th period, respectively, i′,t′ is the output of the i′th power station in the t′th period.

[0180] 6) Ensure output constraints:

[0181]

[0182] in, is the guaranteed output of the i′th power station in the t′th period.

[0183] 7) Water level constraints at the beginning and end of the dispatch period:

[0184]

[0185] in, and are the initial and final water levels of the i′th power station in the entire dispatching period, respectively, i′,0 is the initial water level of the i′th power station, Z i′,T is the final water level of the i′th power station.

[0186] In order to prove the effectiveness of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application, the sine-cosine algorithm (SCA), the repairable grey wolf algorithm (RGWO), the whale algorithm (WOA) and the HHO are selected for comparison. The number of individuals N in the population of all methods is set to 30, the maximum number of evaluations K is set to 30000, and the number of algorithm repetitions R is set to e is 20. In addition, the initial escape energy E0 of the method for ecological dispatching of cascade reservoirs based on chaos enhanced HHO provided in the embodiment of the present application is set to a random number uniformly distributed between -1 and 1, and the crossover probability cr is set to a normally distributed random number with a mean of 0.6 and a standard deviation of 0.1. The following is an analysis of the ecological dispatching method for cascade reservoirs based on chaos enhanced HHO provided in the embodiment of the present application in combination with relevant data, as shown in Table 1:

[0187] Table 1

[0188]

[0189]

[0190] As shown in Table 1, compared with other control methods, the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided by this application is superior to other control methods in most indicators. Specifically, for a water inflow frequency of 75%, the optimal values ​​obtained by this application are 35%, 24%, 7% and 21% lower than those of SCA, RGWO, WOA and HHO, respectively, and the standard deviations are increased by 98%, 98%, 98% and 99%, respectively.

[0191] It is worth noting that although the standard deviation of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in this application is higher at a water inflow frequency of 25% compared with other methods, its overall target value (including optimal value, median, mean and worst value) is smaller. This indicates that there may be more minimum points within the distribution range of better results, which shows that the proposed strategy effectively finds a more accurate solution. Overall, the results of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in this application are significantly better than other technical solutions, showing its superior search performance.

[0192] In order to further verify the effectiveness of the cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in this application, the target values ​​of the five methods at 25%, 50% and 75% water inflow frequencies were statistically repeated 20 times. Figures 3 to 5 As shown. The results show that under all water inflow frequencies, the cascade reservoir ecological operation method based on chaos enhanced HHO provided in this application can always find better and more stable solutions compared with other mature optimization techniques. These observations are also consistent with the results in Table 1.

[0193] Figures 6 to 8 The convergence process curves of different methods at water inflow frequencies of 25%, 50% and 75% are further given. As can be seen from the figure, the SCA method performs the worst at a water inflow frequency of 25%, and performs averagely at water inflow frequencies of 50% and 75%. The HHO method shows average performance at all three water inflow frequencies. In contrast, the cascade reservoir ecological scheduling method based on chaos enhanced HHO provided in the present application shows the best convergence speed and accuracy among the three water inflow frequencies. This fully demonstrates the effectiveness and efficiency of the method proposed in the present application, and is an effective solution tool.

[0194] This application effectively overcomes the technical problems of the original HHO in solving ecological problems of cascade reservoirs, such as reduced individual diversity, low convergence accuracy, and unbalanced exploration and development processes. It can significantly improve the population quality, the balance level of exploration and development, and the exploration ability of the original HHO, and has good engineering practical value.

[0195] The cascade reservoir ecological dispatching method based on chaos enhanced HHO provided in the embodiment of the present application adopts a random difference strategy to update the updated individual position again, so that the obtained individual position is more accurate, and the convergence accuracy of the algorithm is further improved. The cascade reservoir ecological dispatching device based on chaos enhanced HHO provided in the present application is described below. The cascade reservoir ecological dispatching device based on chaos enhanced HHO described below and the cascade reservoir ecological dispatching method based on chaos enhanced HHO described above can refer to each other.

[0196] See also Fig. 9 The embodiment of the present application provides a cascade reservoir ecological scheduling device based on chaos enhanced HHO, which may include: an acquisition module 910, a first generation module 920, a first update module 930, a second update module 940, a third update module 950, a processing module 960 and a second generation module 970.

[0197] An acquisition module 910 is used to determine input parameters of the chaos enhanced Harris Hawk algorithm, where the input parameters at least include a maximum number of evaluations;

[0198] The first generation module 920 is used to generate an initial population based on a chaotic strategy in the search space, and the individuals in the initial population correspond to the decision variables in the ecological dispatching scheme constituting the cascade reservoirs;

[0199] A first updating module 930 is used to update the position of each individual according to the fitness of each individual;

[0200] The second updating module 940 is used to update the global optimal individual position and the historical extreme individual position according to the fitness of each individual;

[0201] A third updating module 950 is used to select different search strategies based on the escape energy and update each individual position;

[0202] Processing module 960, for returning to execute updating of each individual position according to the fitness of each individual, when the number of fitness evaluations of each individual based on the fitness of each individual is less than the maximum evaluation number, until the number of fitness evaluations reaches the maximum evaluation number, and determining an updated global optimal individual position according to each individual position after the fitness evaluation reaches the maximum evaluation number;

[0203] The second generation module 970 is used to determine the optimal ecological scheduling plan of the cascade reservoirs according to the updated global optimal individual position.

[0204] The cascade reservoir ecological dispatching device based on chaos-enhanced HHO provided in the embodiment of the present application generates an initial population based on a chaos strategy in the search space, and then updates the position of each individual according to the fitness of each individual, and updates the global optimal individual position and the historical extreme individual position. According to the escape energy, different search strategies are selected to update the position of each individual. Finally, when it is determined that the number of fitness evaluations reaches the maximum number of evaluations, the updated global optimal individual position is obtained according to the updated position of each individual. Thus, the introduction of chaos strategy in the Harris Eagle algorithm effectively overcomes the problems of reduced individual diversity and low convergence accuracy of the original HHO in solving the ecological problems of cascade reservoirs, increases the diversity of generated individuals, and improves the convergence accuracy of the algorithm.

[0205] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0206] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0207] Based on the method in the above embodiment, the present application embodiment provides an electronic device, see Fig.10 The electronic device may include: a processor (Processor) 1010, a communication interface (Communications Interface) 1020, a memory (Memory) 1030 and a communication bus 1040, wherein the processor 1010, the communication interface 1020, and the memory 1030 communicate with each other through the communication bus 1040. The processor 1010 may call the logic instructions in the memory 1030 to execute the method in the above embodiment.

[0208] In addition, the logic instructions in the above-mentioned memory 1030 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0209] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0210] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0211] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0212] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0213] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0214] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0215] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for ecological regulation of cascade reservoirs based on chaos enhanced HHO, characterized in that: include: Determining input parameters of the chaos enhanced Harris Hawk algorithm, the input parameters including at least a maximum number of evaluations; In the search space, an initial population is generated based on a chaotic strategy, wherein the individuals in the initial population correspond to the decision variables in the ecological dispatching scheme constituting the cascade reservoirs; According to the fitness of each individual, the position of each individual is updated; According to the fitness of each individual, update the global optimal individual position and the historical extreme individual position; Select different search strategies based on the escape energy, and update each individual position; In the case that the number of fitness evaluations of each individual based on the fitness of each individual is less than the maximum evaluation number, returning to execute the updating of each individual position according to the fitness of each individual until the number of fitness evaluations reaches the maximum evaluation number, and in the case that the number of fitness evaluations reaches the maximum evaluation number, determining the updated global optimal individual position according to each individual position after the update; According to the updated global optimal individual position, the optimal ecological scheduling plan of the cascade reservoirs is determined.

2. The method for ecological regulation of cascade reservoirs based on chaos enhanced HHO as claimed in claim 1, characterized in that: The generating of the initial population based on the chaos strategy in the search space includes: Randomly generate N individual positions in the search space based on the chaotic strategy; N individual positions are determined as the initial population.

3. The method for ecological regulation of cascade reservoirs based on chaos enhanced HHO as claimed in claim 1, characterized in that: The updating of each individual position according to the fitness of each individual includes: For any individual: The individual position is updated according to the relationship between the individual fitness in the current fitness evaluation process and the individual fitness in the next fitness evaluation process.

4. The method for ecological regulation of cascade reservoirs based on chaos enhanced HHO as claimed in claim 1, characterized in that: The updating of the global optimal individual position and the historical extreme individual position according to the fitness of each individual includes: Update the global optimal individual position according to the individual position corresponding to the minimum fitness among all individual fitnesses; For any individual, the historical extreme individual position is updated according to the individual position with the minimum fitness obtained during the individual fitness evaluation process.

5. The method for ecological regulation of cascade reservoirs based on chaos enhanced HHO as claimed in claim 1, characterized in that: The step of selecting different search strategies based on the escape energy and updating each individual position includes: When the absolute value of the escape energy is greater than or equal to 1, executing an individual exploration strategy to update the position of each individual; When the absolute value of the escape energy is less than 1, executing the individual utilization strategy to update the position of each individual; Execute the random mutation strategy and update each individual position after the update.

6. The method for ecological regulation of cascade reservoirs based on chaos enhanced HHO as claimed in claim 5, characterized in that: When the absolute value of the escape energy is greater than or equal to 1, the individual exploration strategy is executed to update the position of each individual, including: For any individual: The individual balance factor is used to adaptively adjust the search step size during the individual exploration process to update the individual position; Accordingly, when the absolute value of the escape energy is less than 1, the executing individual utilizes a strategy to update the position of each individual, including: For any individual: Random numbers and the absolute value of the escape energy are used to select individuals for dive search or attack search behavior to update the individual position.

7. The method for ecological regulation of cascade reservoirs based on chaos enhanced HHO as claimed in claim 5, characterized in that: The random mutation strategy is executed to update each individual position after the update, including: For any individual: The random mutation strategy is executed to generate a mutant individual position corresponding to the updated individual position, and based on the crossover probability, the position vector of any dimension in the updated individual position is replaced to update each updated individual position again.

8. A cascade reservoir ecological dispatching device based on chaos enhanced HHO, characterized in that: include: An acquisition module, used for determining input parameters of the chaos enhanced Harris Hawk algorithm, wherein the input parameters at least include a maximum number of evaluations; A first generation module is used to generate an initial population based on a chaotic strategy in a search space, wherein the individuals in the initial population correspond to decision variables in an ecological dispatching scheme constituting the cascade reservoirs; The first updating module is used to update the position of each individual according to the fitness of each individual; The second updating module is used to update the global optimal individual position and the historical extreme individual position according to the fitness of each individual; A third updating module is used to select different search strategies based on the escape energy to update each individual position; A processing module, configured to return to the step of updating each individual position according to the fitness of each individual, when the number of fitness evaluations for each individual based on the fitness of each individual is less than the maximum evaluation number, until the number of fitness evaluations reaches the maximum evaluation number, and determine the updated global optimal individual position according to each individual position after the fitness evaluation reaches the maximum evaluation number; The second generation module is used to determine the optimal ecological scheduling plan of the cascade reservoirs according to the updated global optimal individual positions.

9. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the cascade reservoir ecological scheduling method based on chaos enhanced HHO as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor executes the cascade reservoir ecological scheduling method based on chaos enhanced HHO as described in any one of claims 1 to 7.

Images