Reservoir optimization scheduling method and device based on improved piebald green bird algorithm

Abstract

The invention relates to the technical field of reservoir scheduling, and discloses a reservoir optimization scheduling method and device based on an improved piebald algorithm, and the method comprises the steps: constructing a reservoir optimization scheduling model; wherein the reservoir optimal scheduling model takes the water level of the hydropower station in each time period within the reservoir scheduling period as a decision variable; randomly generating an initialized population; wherein individuals in the initialized population represent the water level of the hydropower station in each time period within the reservoir dispatching deadline; iteratively updating the position of each individual in the initialized population by simulating the inhabiting and hovering behaviors, the diving behavior and the change of predation efficiency of the emerald; and when the iteratively updated population satisfies an iteration stop condition, determining an optimal reservoir scheduling scheme based on the iteratively updated population. According to the method, the problems of algorithm prematurity and local optimum can be effectively avoided, and the optimization efficiency of the reservoir scheduling scheme is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir scheduling, and in particular to a reservoir optimization scheduling method and device based on an improved Pied Kingfisher algorithm. Background Art

[0002] At present, reservoir optimization and scheduling, as a key link in water resources management and utilization, faces many challenges. On the premise of ensuring its own flood control requirements and safe operation, it is also necessary to improve the utilization rate of water resources and give full play to the optimal performance of reservoirs to achieve maximum benefits.

[0003] In order to better solve the problem of reservoir optimization and scheduling, many optimization algorithms have been introduced into this field. However, the relevant reservoir optimization and scheduling algorithms have the problems of premature maturity and falling into local optimality, which affects the solution accuracy and convergence speed of the algorithm, resulting in low optimization efficiency of the reservoir scheduling scheme. Summary of the Invention

[0004] In view of this, the present invention provides a reservoir optimization scheduling method and system based on an improved Pied Kingfisher algorithm to solve the problem of low optimization efficiency of reservoir scheduling schemes.

[0005] In a first aspect, the present invention provides a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm, the method comprising:

[0006] Constructing a reservoir optimization operation model; wherein the reservoir optimization operation model uses the hydropower station water level at each time period within the reservoir operation period as the decision variable;

[0007] Randomly generate an initialization population; the individuals in the initialization population represent the water levels of the hydropower station in each period within the reservoir scheduling period;

[0008] By simulating the changes in the perching and hovering behavior, diving behavior, and predation efficiency of the Pied Kingfisher, the position of each individual in the initialized population is iteratively updated.

[0009] When the iteratively updated population meets the iteration stopping condition, the optimal reservoir scheduling scheme is determined based on the iteratively updated population.

[0010] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment applies the improved Pied Kingfisher optimization algorithm to the field of reservoir scheduling and optimizes the solution of scheduling problems, thereby improving the optimization ability and update efficiency, and can effectively avoid the problems of algorithm premature maturity and falling into local optimality. The position of each individual in the initialized population is iteratively updated by simulating the roosting and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher to achieve improvement of the Pied Kingfisher algorithm, further enhancing the algorithm's exploration and development capabilities, and thus constructing a more efficient intelligent optimization algorithm in the field of reservoir optimization scheduling, thereby improving the optimization efficiency of reservoir scheduling schemes.

[0011] In an optional embodiment, constructing a reservoir optimization operation model includes:

[0012] Obtain characteristic parameters of the hydropower station in the target power transmission system and the load demand of the power transmission grid, and calculate the grid residual load and the grid residual load mean based on the characteristic parameters of the hydropower station and the load demand of the power transmission grid;

[0013] Taking the minimum mean square error of grid residual load within the reservoir dispatch period as the goal, the objective function is constructed based on the grid residual load and the mean value of grid residual load;

[0014] Constructing the constraints of the objective function based on the characteristic parameters of the hydropower station;

[0015] Taking the water level of the hydropower station in each period within the reservoir operation period as the decision variable, a reservoir optimization operation model is constructed based on the objective function and constraint conditions.

[0016] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment constructs an objective function based on the grid residual load and the grid residual load mean, constructs the constraint conditions of the objective function based on the characteristic parameters of the hydropower station, and uses the hydropower station water level in each period within the reservoir scheduling period as the decision variable. This allows the optimal reservoir scheduling plan to reasonably arrange the power generation plan based on the demand of the power market and the water inflow conditions of the reservoir, so that the hydropower station can achieve optimal power generation operation under different water levels, improve the conversion efficiency of water energy resources, and increase power generation and power generation revenue.

[0017] In an optional embodiment, the position of each individual in the initialized population is iteratively updated by simulating the perching and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher, including:

[0018] The reservoir optimization operation model is used to calculate the fitness value of each individual in the initial population, and the individual corresponding to the minimum fitness value is taken as the initial global optimal solution;

[0019] The initial global optimal solution is compared with a first preset threshold and a second preset threshold, and the position of each individual in the initialized population is updated by simulating the perching and hovering behavior of the Pied Kingfisher based on the comparison results; wherein the second preset threshold is less than the first preset threshold;

[0020] By simulating the diving behavior of the Pied Kingfisher, the position of each individual in the updated population is updated again;

[0021] Optimize the predation efficiency of the Pied Kingfisher and use the optimized predation efficiency to update the individual positions of the updated population;

[0022] The fitness value of each individual in the population after the individual position is updated is sorted, and individuals are reselected based on the sorting result to form the population of the next iteration cycle, and the position of each individual in the population of the next iteration cycle is iteratively updated.

[0023] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment, in the process of simulating the changes in the roosting and hovering behavior, diving behavior and predation efficiency of the Pied Kingfisher, updates the individual positions in the initialized population three times, thereby improving the optimization ability of the Pied Kingfisher algorithm and the updating efficiency of the individual positions, and can effectively solve the problems of premature maturity and being trapped in local optimality; among them, by optimizing the predation efficiency of the Pied Kingfisher, the dynamic adaptability of the algorithm is improved, and the global exploration and local development capabilities of the algorithm are balanced; by reselecting individuals to form the population of the next iteration cycle based on the sorting results, the vitality and diversity of the population are effectively maintained, so that the algorithm can escape the local optimality and increase the possibility of finding a better solution.

[0024] In an optional embodiment, the initial global optimal solution is compared with a first preset threshold and a second preset threshold respectively, and the position of each individual in the initialized population is updated based on the comparison results, including:

[0025] If the initial global optimal solution is greater than the first preset threshold, the simulated annealing algorithm is used to update the position of each individual in the initialized population;

[0026] Alternatively, if the initial global optimal solution is less than a first preset threshold and the initial global optimal solution is greater than a second preset threshold, a hovering strategy is used to update the position of each individual in the initialized population;

[0027] Alternatively, if the initial global optimal solution is less than a second preset threshold, the position of each individual in the initialized population is updated using a habitat strategy.

[0028] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment compares the initial global optimal solution with the first preset threshold and the second preset threshold respectively, and determines different exploration methods based on the comparison results, so that individual positions can be updated in different ways during the exploration phase, thereby increasing the flexibility and diversity of the search, helping to escape the local optimal trap, and improving the global search capability of the algorithm.

[0029] In an optional embodiment, if the initial global optimal solution is greater than a first preset threshold, a simulated annealing algorithm is used to update the position of each individual in the initialized population, including:

[0030] Get the initial temperature, cooling rate and stop condition;

[0031] Randomly perturb the initial global optimal solution to obtain a new solution;

[0032] Determine a fitness difference based on the initial global optimal solution and the new solution, and compare the fitness difference with zero;

[0033] If the fitness difference is greater than zero, the acceptance probability is determined based on the fitness difference and the initial temperature, and the new solution is accepted based on the acceptance probability;

[0034] The temperature is gradually lowered according to the cooling rate. If the current temperature reaches the stopping condition, a new solution is output and used as the population after updating the position of each individual.

[0035] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment searches for the global optimal solution by gradually lowering the system temperature, accepts inferior solutions according to a certain probability, and finally converges to the global optimal solution, thereby updating the position of each individual in the initialized population, avoiding the problem of individuals in the initialized population falling into local optimality, promoting the exploration of the solution space, and thus improving the algorithm's optimization ability.

[0036] In an optional embodiment, randomly generating an initialization population includes:

[0037] In the search space, the Logistic chaotic map is used to generate the initial population.

[0038] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment uses Logistic Chaotic Mapping to generate a uniform and dispersed initialization population in the search space, which helps to avoid excessive aggregation of individuals and can reduce the "hole" areas caused by random fluctuations, which is beneficial to improving the search capability of the Pied Kingfisher algorithm.

[0039] In a second aspect, the present invention provides a reservoir optimization scheduling device based on an improved Pied Kingfisher algorithm, the device comprising:

[0040] A construction module is used to construct a reservoir optimization operation model; wherein the reservoir optimization operation model uses the water level of the hydropower station in each period within the reservoir operation period as a decision variable;

[0041] A generation module is used to randomly generate an initialization population; wherein the individuals in the initialization population represent the water level of the hydropower station in each period within the reservoir scheduling period;

[0042] An iterative update module is used to iteratively update the position of each individual in the initialized population by simulating the perching and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher;

[0043] The determination module is used to determine the optimal reservoir scheduling plan based on the iteratively updated population when the iteratively updated population meets the iteration stopping condition.

[0044] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the reservoir optimization scheduling method and system based on the improved Pied Kingfisher algorithm of the above-mentioned first aspect or any corresponding embodiment thereof.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, and the computer instructions are used to enable a computer to execute the reservoir optimization scheduling method and system based on the improved Pied Kingfisher algorithm of the above-mentioned first aspect or any corresponding embodiment thereof.

[0046] In a fifth aspect, the present invention provides a computer program product comprising computer instructions, which are used to enable a computer to execute the reservoir optimization scheduling method and system based on the improved Pied Kingfisher algorithm of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 1 is a flow chart of a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm according to an embodiment of the present invention;

[0049] Figure 2is a flow chart of another reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm according to an embodiment of the present invention;

[0050] Figure 3 1 is a flow chart of another reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm according to an embodiment of the present invention;

[0051] Figure 4 3. It is a workflow diagram of a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm according to an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of the performance comparison results of the Pied Kingfisher algorithm and the improved Pied Kingfisher algorithm on typical day 1;

[0053] Figure 6 This is a schematic diagram of the performance comparison results of the Pied Kingfisher algorithm and the improved Pied Kingfisher algorithm on typical day 2;

[0054] Figure 7 is a schematic diagram of the performance comparison results of the Pied Kingfisher algorithm and the improved Pied Kingfisher algorithm on typical day 3;

[0055] Figure 8 is a schematic diagram of the performance comparison results of the Pied Kingfisher algorithm and the improved Pied Kingfisher algorithm on typical day 4;

[0056] Figure 9 2 is a structural block diagram of a reservoir optimization scheduling device based on an improved Pied Kingfisher algorithm according to an embodiment of the present invention;

[0057] Figure 10 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0059] With the continuous improvement of intelligent technology, more and more intelligent optimization algorithms are being proposed and playing an important role in many fields. Inspired by the sociality of biological groups and physical phenomena, a number of bionic intelligent optimization algorithms such as the ant colony optimization algorithm, the cuckoo optimization algorithm, the whale optimization algorithm, and the gray wolf optimization algorithm have been proposed. These algorithms have been widely used in transportation, image processing, reservoir optimization scheduling and other fields.

[0060] In order to better solve the problem of reservoir optimization and scheduling, many optimization algorithms have been introduced into this field; for example, the introduction of genetic algorithms into the optimization and scheduling of large reservoirs has greatly solved the spatiotemporal problems of large reservoirs; based on the principle of dynamic programming, the reservoir optimization and scheduling problem is simplified into multi-stage sub-problems, and the particle swarm algorithm is introduced to solve the sub-problems, which fully demonstrates the collaborative advantages of different intelligent algorithms; however, the above-mentioned optimization algorithms often undergo 1 to 2 update processes in each iteration. The fewer updates limit the global exploratory ability of the algorithm and easily cause the algorithm to fall into a local optimal solution.

[0061] To solve the above technical problems, an embodiment of the present invention provides a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm. The Pied Kingfisher Algorithm (PKO) has demonstrated significant advantages in machine learning, image processing and other fields due to its unique search mechanism and good performance. The algorithm simulates the foraging behavior of Pied Kingfishers in nature to effectively solve complex problems. The embodiment of the present invention applies the Pied Kingfisher Algorithm to the field of reservoir scheduling, utilizes the three-step update process in the Pied Kingfisher Algorithm to solve the problem of falling into local optimality, and then utilizes the excellent mechanism of multiple exploration and development in the improved Pied Kingfisher Algorithm to generate a more reasonable and efficient scheduling plan.

[0062] An embodiment of the present invention provides a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm. It should be noted that the reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided by the embodiment of the present invention, its execution subject can be a reservoir optimization scheduling device based on the improved Pied Kingfisher algorithm, and the reservoir optimization scheduling device based on the improved Pied Kingfisher algorithm can be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device can be a server or a terminal, wherein the server in the embodiment of the present application can be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, and other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0063] According to an embodiment of the present invention, an embodiment of a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0064] In this embodiment, a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm is provided, which can be used for the above-mentioned electronic device. Figure 1is a flow chart of a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0065] Step S101, constructing a reservoir optimization scheduling model; wherein the reservoir optimization scheduling model uses the water level of the hydropower station in each period within the reservoir scheduling period as a decision variable.

[0066] Step S102: randomly generating an initialization population; wherein the individuals in the initialization population represent the water level of the hydropower station in each period within the reservoir scheduling period.

[0067] Step S103 , iteratively updating the position of each individual in the initialized population by simulating the perching and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher.

[0068] Specifically, the Pied Kingfisher has unique hunting behaviors and symbiotic relationships, with three main renewal stages including: perching and hovering, diving strategy, and symbiotic stage.

[0069] Step S104: When the iteratively updated population meets the iteration stopping condition, an optimal reservoir scheduling scheme is determined based on the iteratively updated population.

[0070] Specifically, it is determined whether the population after iterative update reaches the maximum number of iterations. If not, the number of iterations is increased and the iterative update is repeated again. If the maximum number of iterations is reached, the population after iterative update is used as the global optimal solution, and the optimal reservoir scheduling plan is determined.

[0071] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment applies the improved Pied Kingfisher optimization algorithm to the field of reservoir scheduling and optimizes the solution of scheduling problems, thereby improving the optimization ability and update efficiency, and can effectively avoid the problems of algorithm premature maturity and falling into local optimality. The position of each individual in the initialized population is iteratively updated by simulating the roosting and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher to achieve improvement of the Pied Kingfisher algorithm, further enhancing the algorithm's exploration and development capabilities, and thus constructing a more efficient intelligent optimization algorithm in the field of reservoir optimization scheduling, thereby improving the optimization efficiency of reservoir scheduling schemes.

[0072] In this embodiment, a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm is provided, which can be used for the above-mentioned electronic device. Figure 2 is a flow chart of a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0073] Step S201: constructing a reservoir optimization scheduling model; wherein the reservoir optimization scheduling model uses the water level of the hydropower station in each period within the reservoir scheduling period as a decision variable.

[0074] Specifically, the above step S201 includes:

[0075] Step S2011: Acquire characteristic parameters of the hydropower station in the target power transmission system and the load demand of the power transmission grid, and calculate the grid residual load and the grid residual load mean based on the characteristic parameters of the hydropower station and the load demand of the power transmission grid.

[0076] Specifically, the characteristic parameters of the hydropower station in the target power transmission system and the load demand of the power transmission grid are read; among them, the characteristic parameters of the hydropower station include: normal water storage level, water level and storage capacity curve of the reservoir, discharge capacity curve and inflow during the scheduling period, and the load demand of the power transmission grid is the electricity demand in the power supply area of ​​the hydropower station.

[0077] Furthermore, the calculation formulas for the grid residual load and the grid residual load mean are as follows:

[0078]

[0079] Among them, P t is the grid load demand, R t is the grid residual load, is the mean residual load of the power grid, T is the total number of time periods in the reservoir dispatch cycle, t is the time period sequence number, t∈[1,T], M t Contribute to the hydropower station.

[0080] Step S2012 , taking the minimum mean square error of the grid residual load within the reservoir dispatch period as the goal, constructing an objective function based on the grid residual load and the grid residual load mean.

[0081] Specifically, the goal is to minimize the mean square error of the grid residual load within the reservoir scheduling period. The fitness value is the objective function value. The decision variable is the hydropower station water level in each period within the reservoir scheduling period. The constraint conditions are constructed based on the characteristic parameters of the hydropower station. The expression of the objective function F is:

[0082]

[0083] Step S2013: constructing constraint conditions of the objective function based on characteristic parameters of the hydropower station.

[0084] Specifically, the constraints include:

[0085] 1) Reservoir water level constraints:

[0086]

[0087] Among them, Z trepresents the water level in front of the reservoir at period t (i.e. the water level of the hydropower station at period t within the reservoir scheduling period), and are the upper and lower limits of the water level in front of the dam of the reservoir in period t.

[0088] 2) Water balance constraints:

[0089] V t =V t-1 +(I t -Q t )·Δt (4)

[0090] Among them, V t and V t-1 Represent the storage capacity of the reservoir in period t and period t-1 respectively, I t represents the inflow to the reservoir during period t, Q t represents the outflow of the reservoir during period t.

[0091] 3) Reservoir characteristic constraints:

[0092]

[0093] Among them, Z t is the average water level upstream of the reservoir during period t, is the average tailwater level downstream of the reservoir during period t, f ZV (Z t ),f ZQ (Q t ) represent the water level-storage capacity curve and tailwater level-discharge flow curve of the reservoir respectively.

[0094] 4) Output characteristic constraints:

[0095]

[0096] in, Represents the reservoir output calculation function, H t is the net water head of the reservoir in period t, is the power generation reference flow of the reservoir in period t.

[0097] 5) Traffic Constraints:

[0098]

[0099] in, and They represent the upper and lower limits of the reservoir discharge flow in period t, Q t represents the outflow of the reservoir in period t.

[0100] 6) Hydropower station output constraints:

[0101]

[0102] in, and They represent the upper and lower limits of the reservoir output in period t, Represents the output of the reservoir in period t.

[0103] In step S2014, the water level of the hydropower station in each period within the reservoir operation period is used as a decision variable, and a reservoir optimization operation model is constructed based on the objective function and constraint conditions.

[0104] Step S202: randomly generate an initial population; wherein, the individuals in the initial population represent the water level of the hydropower station in each period within the reservoir scheduling period. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0105] Step S203, by simulating the roosting and hovering behavior, diving behavior and changes in predation efficiency of the Pied Kingfisher, the position of each individual in the initialized population is iteratively updated. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0106] Step S204: When the iteratively updated population meets the iteration stop condition, the optimal reservoir operation scheme is determined based on the iteratively updated population. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0107] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment constructs an objective function based on the grid residual load and the grid residual load mean, constructs the constraint conditions of the objective function based on the characteristic parameters of the hydropower station, and uses the hydropower station water level in each period within the reservoir scheduling period as the decision variable. This allows the optimal reservoir scheduling plan to reasonably arrange the power generation plan based on the demand of the power market and the water inflow conditions of the reservoir, so that the hydropower station can achieve optimal power generation operation under different water levels, improve the conversion efficiency of water energy resources, and increase power generation and power generation revenue.

[0108] In this embodiment, a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm is provided, which can be used for the above-mentioned electronic device. Figure 3 is a flow chart of a reservoir optimization scheduling method based on an improved Pied Kingfisher algorithm according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0109] Step S301: Construct a reservoir optimization operation model; wherein the reservoir optimization operation model uses the water level of the hydropower station in each period within the reservoir operation period as the decision variable. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0110] Step S302: randomly generating an initialization population; wherein the individuals in the initialization population represent the water level of the hydropower station in each period within the reservoir scheduling period.

[0111] Specifically, the parameters of the improved Pied Kingfisher algorithm are set, the initialization population size is N, the individual dimension is D, and the number of algorithm iterations is Max_Iter; wherein, in the search space, the Logistic (logical) chaotic map is used to generate the initialization population, that is, N individuals are generated by initialization through the Logistic chaotic map, that is, the initialization population contains N individuals, and each individual represents the water level of the hydropower station in each period within the reservoir scheduling period.

[0112] Furthermore, the Logistic chaotic map first generates a chaotic sequence according to the following formula:

[0113] x n+1 =μx n (1-x n ) (9)

[0114] Among them, x n is a generated random number, x n+1 is the random number to be generated, μ is the chaotic parameter, and to ensure chaotic behavior, μ=4. At the same time, the initial value x0 needs to be selected from (0, 1).

[0115] Furthermore, the chaotic sequence is mapped to the solution space of the decision variables in the problem to be optimized:

[0116] y n =lb+x n ×(ub-lb) (10)

[0117] Among them, y n To initialize the individuals in the population, ub and lb are the search space range of the individuals in a certain dimension, which is [lb, ub].

[0118] Step S303 , iteratively updating the position of each individual in the initialized population by simulating the perching and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher.

[0119] Specifically, the above step S303 includes:

[0120] Step S3031: Calculate the fitness value of each individual in the initial population using the reservoir optimization scheduling model, and take the individual corresponding to the minimum fitness value as the initial global optimal solution.

[0121] Specifically, the fitness value of each individual in the initialized population is calculated through the reservoir optimization scheduling model. Since the reservoir optimization scheduling model aims to minimize the mean square error of the grid surplus load within the reservoir scheduling period, the individual with the smallest fitness value is selected as the initial global optimal solution.

[0122] Step S3032, compare the initial global optimal solution with the first preset threshold and the second preset threshold respectively, simulate the perching and hovering behavior of the Pied Kingfisher based on the comparison results, and update the position of each individual in the initialized population; wherein the second preset threshold is less than the first preset threshold.

[0123] In some optional embodiments, such as Figure 4 As shown, the above step S3032 includes:

[0124] Step a1: If the initial global optimal solution is greater than a first preset threshold, the simulated annealing algorithm is used to update the position of each individual in the initialized population;

[0125] Specifically, assuming that the first preset threshold is 0.8, if the initial global optimal solution rand(0,1)>0.8, the simulated annealing algorithm is used to update the position of each individual in the initialized population. The simulated annealing algorithm is an optimization algorithm based on random search. It imitates the metal annealing process and searches for the target optimal solution by gradually lowering the system temperature. It accepts inferior solutions according to a certain probability and finally converges to the global optimal solution.

[0126] Furthermore, the specific steps of the simulated annealing algorithm include: obtaining an initial temperature, a cooling rate and a stopping condition; randomly perturbing the initial global optimal solution to obtain a new solution; determining a fitness difference based on the initial global optimal solution and the new solution, and comparing the fitness difference with zero; if the fitness difference is greater than zero, determining an acceptance probability based on the fitness difference and the initial temperature, and accepting the new solution based on the acceptance probability; gradually lowering the temperature according to the cooling rate, and if the current temperature reaches the stopping condition, outputting the new solution, and using the new solution as the population after updating the position of each individual.

[0127] Furthermore, in the initialization phase of the simulated annealing algorithm, the initial temperature, cooling rate, and stopping condition are determined. The selection of these parameters will affect the breadth and convergence speed of the algorithm search process. In the iterative phase, the initial global optimal solution is perturbed slightly to explore a new solution space and randomly generate a new solution in the space. The position formula of the new solution is as follows:

[0128] X i (t+1)=X i (t)+δ (11)

[0129] Among them, δ represents a small random perturbation, δ ∈ U(0, 1), and X i (t) represents the initial global optimal solution, and X i (t + 1) represents the new solution.

[0130] Furthermore, the search direction is determined by evaluating the quality of the new solution and the initial global optimal solution, and whether to accept the new solution is decided according to a certain probability. This mechanism allows the algorithm to accept some inferior solutions in the early stage to avoid falling into local optima, thereby promoting the exploration of the solution space. The calculation formula for the probability P of whether to accept the new solution is as follows:

[0131]

[0132] Among them, T current is the current temperature, ΔE is the fitness difference, representing the quality difference between the initial global optimal solution and the new solution, and is used to measure whether the new solution is better or worse than the initial global optimal solution.

[0133] Furthermore, in the temperature update stage, the temperature will gradually decrease as the iteration progresses, enabling the simulated annealing algorithm to focus more on the local search of better solutions. The decrease in temperature will reduce the probability of accepting bad solutions, prompting the simulated annealing algorithm to gradually converge to a stable solution. In each round of iteration, according to the temperature update formula of the cooling strategy as follows:

[0134] T new = T current ×α cool (13)

[0135] Among them, T new represents the updated temperature, and α cool represents the cooling rate, which is used to control the speed of temperature decrease.

[0136] Step a2, or, if the initial global optimal solution is less than the first preset threshold and the initial global optimal solution is greater than the second preset threshold, then the hovering strategy is adopted to update the position of each individual in the initialized population;

[0137] Specifically, assuming that the second preset threshold is 0.4, if 0.4 < rand(0, 1) ≤ 0.8, then the hovering strategy is adopted to calculate the parameter C to update the position of each individual in the initialized population. Among them, the parameter C plays a key role. The parameter C is dynamically determined according to the current strategy and can be "perching" or "hovering". The calculation of the parameter C is tailored for each strategy to ensure the best performance in different operating modes. The calculation formula for the parameter C under the hovering strategy is as follows:

[0138]

[0139]

[0140] Among them, Fitness(i) and Fitness(j) represent the fitness values ​​of the i-th and j-th individuals in the initialization population, respectively. _ rate represents predation behavior, and BF represents a constant value.

[0141] Step a3: Alternatively, if the initial global optimal solution is less than a second preset threshold, a habitat strategy is used to update the position of each individual in the initialized population.

[0142] Specifically, if rand(0,1)≤0.4, the habitat strategy is adopted to calculate the parameter C under the habitat strategy, thereby updating the position of each individual in the initialized population.

[0143] Furthermore, the calculation formula of parameter C under the habitat strategy is as follows:

[0144]

[0145] Among them, the constant value BF is set to 8, and rand represents a random value between 0 and 1.

[0146] Furthermore, the formula for updating the position of each individual in the initialized population is:

[0147] X i ′(t+1)=X i (t)+α×C×(X j (t)-X i (t)),i,j=1,2,…,Nandj≠i (17)

[0148] Among them, X i ′(t+1) represents the updated individual position, that is, the individual water level process after the change, X i (t) and X j (t) represents the current position of individual i and individual j respectively, α represents a parameter whose value is 2×randn(1, dim), randn represents a normally distributed random number, and dim represents the data dimension of the random number.

[0149] Step S3033: Update the position of each individual in the updated population again by simulating the diving behavior of the Pied Kingfisher.

[0150] Specifically, the diving behavior of the Pied Kingfisher makes it an efficient hunter. In this stage, the Pied Kingfisher uses its excellent diving strategy to update the position of each individual in the population again, and the decision variables are further updated accordingly, and the objective function value is also further updated. This stage simulates the Pied Kingfisher's rapid diving behavior to catch fish for more refined local search.

[0151] Furthermore, the calculation formula for re-updating the position of each individual in the updated population is as follows:

[0152] X i ″(t+1)=X i ′(t)+HA×o×γ×(bX best (t))i=1,2,...,N (18)

[0153] α=2×randn(1,dim)-1 (19)

[0154]

[0155] b=X i ′(t)+o 2 ×rand×X best (t) (22)

[0156] Among them, X i ″(t+1) represents the position of each individual in the updated population after the position is updated again, γ represents the control parameter, HA represents the hunting ability, o represents the time decay factor, b represents the guide item of the local optimal direction, Best_Fitness represents the optimal fitness value, X best (t) represents the water level process corresponding to the individual with the optimal fitness value.

[0157] Step S3034: Optimize the predation efficiency of the Pied Kingfisher, and use the optimized predation efficiency to update the individual positions of the updated population.

[0158] Specifically, after entering the symbiotic stage of the Pied Kingfisher, the individual positions of the population will further change according to the predation strategy of this stage. A random number is generated based on the individuals of the updated population, and whether the individual positions of the updated population need to be further updated is determined by judging whether the random number is greater than 1-PE (optimized predation efficiency). If the random number is greater than 1-PE, the individual positions of the updated population are updated, and the decision variables and fitness values ​​are further updated. Otherwise, the decision variables are not updated.

[0159] Furthermore, the calculation formula of the optimized predation efficiency PE is as follows:

[0160]

[0161] Among them, PE max Indicates the maximum predation efficiency, PE min represents the minimum predation efficiency.

[0162] Furthermore, the calculation formula for individual position update is as follows:

[0163]

[0164] Among them, X i ″′(t+1) represents the individual position after the individual position is updated using the optimized predation efficiency, X m (t) and X n (t) represents two individuals randomly selected from the updated population.

[0165] Step S3035, sorting the fitness value of each individual in the population after the individual position is updated, reselecting individuals to form the population of the next iteration cycle based on the sorting result, and iteratively updating the position of each individual in the population of the next iteration cycle.

[0166] Specifically, after completing the three stages of predation by the pied kingfisher, the fitness values ​​calculated for each individual in the population after the individual position is updated are sorted, and 10% of individuals with poor fitness values ​​are selected and re-initialized. Reinitializing individuals with poor fitness can enable the search space to be more fully explored, enhance the global search capability, and help the algorithm escape the trap of local optimal solutions.

[0167] Step S304: When the iteratively updated population meets the iteration stopping condition, an optimal reservoir scheduling scheme is determined based on the iteratively updated population.

[0168] Specifically, it is determined whether the current number of iterations has reached the maximum number of iterations. If not, the number of iterations is increased and the iterative calculation is performed again. If the maximum number of iterations is reached, the global optimal position is determined and the global optimal solution is output as the optimal scheduling plan for reservoir optimization scheduling.

[0169] The reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm provided in this embodiment, in the process of simulating the changes in the roosting and hovering behavior, diving behavior and predation efficiency of the Pied Kingfisher, updates the individual positions in the initialized population three times, thereby improving the optimization ability of the Pied Kingfisher algorithm and the updating efficiency of the individual positions, and can effectively solve the problems of premature maturity and being trapped in local optimality; among them, by optimizing the predation efficiency of the Pied Kingfisher, the dynamic adaptability of the algorithm is improved, and the global exploration and local development capabilities of the algorithm are balanced; by reselecting individuals to form the population of the next iteration cycle based on the sorting results, the vitality and diversity of the population are effectively maintained, so that the algorithm can escape the local optimality and increase the possibility of finding a better solution.

[0170] The following is an example of a specific embodiment to illustrate the specific steps of the reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm.

[0171] Example 1:

[0172] Hydropower Station A was selected, and February 5, 2022 (typical day 1) and May 10, 2022 (typical day 2) were selected as typical days in the dry season, and August 4, 2021 (typical day 3) and October 19, 2021 (typical day 4) were selected as typical days in the flood season. With the day as the scheduling period and the 2-hour scheduling time scale, and the minimum mean square error of the hydropower station residual load as the objective function, a peak-shaving optimization scheduling model for the hydropower station was established. The improved Pied Kingfisher Optimizer (IMPKO) algorithm was used for solution calculation. A comparative experiment was conducted with the unimproved Pied Kingfisher algorithm to verify the effectiveness of the improved IMPKO. The specific solution process is as follows:

[0173] Set the algorithm parameters, that is, set the population size to N = 50, the maximum number of iterations M = 100, the maximum predation efficiency to 0.9, and the minimum predation efficiency to 0.1; in IMPKO, the attenuation factor is 0.3, the attenuation speed parameter is 0.1, the simulated annealing initial temperature T is 1000 ° C, and the cooling rate α is 0. cool is 0.9.

[0174] The residual load mean square error is a key indicator for measuring load fluctuations in the power system. The smaller the value, the smoother the load fluctuation, and vice versa. In reservoir optimization scheduling, using the residual load mean square error as the objective function means that the scheduling strategy is committed to achieving grid load stabilization and reducing severe load fluctuations, which is conducive to ensuring the stable operation of the power system and avoiding the risk of power supply instability or even power system collapse caused by excessive load fluctuations. The comparison results of the objective function calculation results of the unimproved Pied Kingfisher algorithm and the improved Pied Kingfisher algorithm on each typical day are shown in Table 1 below:

[0175] Table 1:

[0176]

[0177] As shown in Table 1 above, compared with the unimproved Pied Kingfisher algorithm, the improved Pied Kingfisher algorithm performs better in both the mean square error of residual load and the peak-to-valley difference of residual load, indicating that the improved Pied Kingfisher algorithm has stronger optimization capabilities in grid load optimization, and the optimized grid load is more stable.

[0178] like Figure 5-8 As shown in the figure, on the four typical days of the dry season and flood season, the mean square error of residual load and the peak-to-valley difference of residual load calculated by the IMPKO algorithm are smaller than those of the unimproved PKO algorithm, indicating that the IMPKO algorithm is easier to find the optimal solution in the optimization process than the PKO algorithm, and the solution has better stability. It also shows that the improved IMPKO algorithm can make the residual load fluctuation more stable in the reservoir peak regulation optimization scheduling, which is conducive to the stable operation of the power system, reduce the risk of power supply instability or power system collapse caused by load fluctuations, and is conducive to improving the operation efficiency and economic benefits of the power system. In addition, the stability, convergence speed and the quality of the solution of the improved IMPKO algorithm are all higher than those of the unimproved PKO algorithm.

[0179] In summary, the improved strategy adopted by the IMPKO algorithm has greatly improved the quality of the algorithm's optimization results and the convergence speed. It also verifies that the IMPKO algorithm has a good optimization effect in reservoir optimization scheduling problems.

[0180] In this embodiment, a reservoir optimization scheduling device based on an improved Pied Kingfisher algorithm is also provided. The device is used to implement the above-mentioned embodiments and preferred embodiments, and the details already described are not repeated here. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0181] This embodiment provides a reservoir optimization scheduling device based on the improved Pied Kingfisher algorithm. Figure 9 Shown, including:

[0182] The construction module 901 is used to construct a reservoir optimization operation model; wherein the reservoir optimization operation model uses the water level of the hydropower station in each period within the reservoir operation period as a decision variable.

[0183] The generation module 902 is used to randomly generate an initialization population; wherein the individuals in the initialization population represent the water level of the hydropower station in each period within the reservoir scheduling period.

[0184] The iterative updating module 903 is used to iteratively update the position of each individual in the initialized population by simulating the perching and hovering behavior, diving behavior and changes in predation efficiency of the Pied Kingfisher.

[0185] The determination module 904 is configured to determine an optimal reservoir scheduling scheme based on the iteratively updated population when the iteratively updated population satisfies an iteration stopping condition.

[0186] In some optional implementations, the building block 901 includes:

[0187] The calculation unit is used to obtain characteristic parameters of the hydropower station in the target power transmission system and the load demand of the power transmission grid, and calculate the grid residual load and the grid residual load mean based on the characteristic parameters of the hydropower station and the load demand of the power transmission grid.

[0188] The first construction unit is used to construct an objective function based on the grid residual load and the grid residual load mean value with the goal of minimizing the mean square error of the grid residual load within the reservoir scheduling period.

[0189] The second construction unit is used to construct the constraint conditions of the objective function based on the characteristic parameters of the hydropower station.

[0190] The third construction unit is used to construct a reservoir optimization scheduling model based on the objective function and constraint conditions, taking the water level of the hydropower station in each period within the reservoir scheduling period as the decision variable.

[0191] In some optional implementations, the construction module 903 includes:

[0192] The second calculation unit is used to calculate the fitness value of each individual in the initialization population using the reservoir optimization scheduling model, and take the individual corresponding to the minimum fitness value as the initial global optimal solution.

[0193] A comparison unit is used to compare the initial global optimal solution with a first preset threshold and a second preset threshold, respectively, simulate the perching and hovering behavior of the pied kingfisher based on the comparison results, and update the position of each individual in the initialized population; wherein the second preset threshold is less than the first preset threshold.

[0194] The updating unit is used to update the position of each individual in the updated population by simulating the diving behavior of the pied kingfisher.

[0195] The optimization unit is used to optimize the predation efficiency of the Pied Kingfisher and use the optimized predation efficiency to update the individual positions of the updated population.

[0196] The sorting unit is used to sort the fitness value of each individual in the population after the individual position is updated, reselect individuals to form the population of the next iteration cycle based on the sorting result, and iteratively update the position of each individual in the population of the next iteration cycle.

[0197] In some optional embodiments, the comparison unit includes:

[0198] The first updating subunit is used to update the position of each individual in the initialized population using a simulated annealing algorithm if the initial global optimal solution is greater than a first preset threshold.

[0199] The second updating subunit is used to update the position of each individual in the initialized population using a hovering strategy if the initial global optimal solution is smaller than the first preset threshold and the initial global optimal solution is larger than the second preset threshold.

[0200] The third updating subunit is configured to update the position of each individual in the initialized population by adopting a habitat strategy if the initial global optimal solution is less than a second preset threshold.

[0201] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0202] The reservoir optimization scheduling device based on the improved Pied Kingfisher algorithm in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0203] The embodiment of the present invention also provides a computer device having the above Figure 9 The reservoir optimization scheduling device based on the improved Pied Kingfisher algorithm is shown.

[0204] See also Figure 10 , Figure 10 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 10As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of a GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 10 A processor 10 is taken as an example.

[0205] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0206] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0207] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0208] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0209] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 10 The bus connection is taken as an example.

[0210] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0211] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0212] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0213] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm, characterized in that: The method comprises: Constructing a reservoir optimization operation model; wherein the reservoir optimization operation model uses the water level of the hydropower station in each period within the reservoir operation period as a decision variable; Randomly generating an initialization population; wherein the individuals in the initialization population represent the water level of the hydropower station in each period within the reservoir scheduling period; Iteratively updating the position of each individual in the initialized population by simulating the perching and hovering behavior, diving behavior, and changes in predation efficiency of the Pied Kingfisher; When the iteratively updated population meets the iteration stopping condition, the optimal reservoir scheduling scheme is determined based on the iteratively updated population.

2. The method according to claim 1, characterized in that The construction of the reservoir optimization operation model includes: Acquiring characteristic parameters of a hydropower station in a target power transmission system and a load demand of a power transmission grid, and calculating a grid residual load and a grid residual load mean based on the characteristic parameters of the hydropower station and the load demand of the power transmission grid; Taking the minimum mean square error of the grid residual load within the reservoir dispatch period as the goal, constructing an objective function based on the grid residual load and the mean value of the grid residual load; Constructing constraint conditions of the objective function based on characteristic parameters of the hydropower station; The reservoir optimization scheduling model is constructed based on the objective function and the constraint conditions, taking the water level of the hydropower station in each period within the reservoir scheduling period as the decision variable.

3. The method according to claim 1, characterized in that The method iteratively updates the position of each individual in the initialized population by simulating the changes in the perching and hovering behavior, diving behavior, and predation efficiency of the Pied Kingfisher, including: Calculating the fitness value of each individual in the initialized population using the reservoir optimization operation model, and taking the individual corresponding to the minimum fitness value as the initial global optimal solution; Comparing the initial global optimal solution with a first preset threshold and a second preset threshold, respectively, simulating the perching and hovering behavior of the Pied Kingfisher based on the comparison results, and updating the position of each individual in the initialized population; wherein the second preset threshold is less than the first preset threshold; By simulating the diving behavior of the Pied Kingfisher, the position of each individual in the updated population is updated again; Optimizing the predation efficiency of the Pied Kingfisher, and using the optimized predation efficiency to update the individual positions of the updated population; The fitness value of each individual in the population after the individual position is updated is sorted, individuals are reselected to form the population of the next iteration cycle based on the sorting result, and the position of each individual in the population of the next iteration cycle is iteratively updated.

4. The method according to claim 3, characterized in that The step of comparing the initial global optimal solution with a first preset threshold and a second preset threshold, and updating the position of each individual in the initialized population based on the comparison results, includes: If the initial global optimal solution is greater than the first preset threshold, the position of each individual in the initialized population is updated using a simulated annealing algorithm; Alternatively, if the initial global optimal solution is smaller than the first preset threshold and the initial global optimal solution is larger than the second preset threshold, a hovering strategy is adopted to update the position of each individual in the initialized population; Alternatively, if the initial global optimal solution is smaller than the second preset threshold, a habitat strategy is adopted to update the position of each individual in the initialized population.

5. The method according to claim 4, characterized in that If the initial global optimal solution is greater than the first preset threshold, the position of each individual in the initialized population is updated using a simulated annealing algorithm, including: Get the initial temperature, cooling rate and stop condition; Performing random perturbations on the initial global optimal solution to obtain a new solution; determining a fitness difference based on the initial global optimal solution and the new solution, and comparing the fitness difference with zero; If the fitness difference is greater than zero, determining an acceptance probability based on the fitness difference and the initial temperature, and accepting the new solution based on the acceptance probability; The temperature is gradually lowered according to the cooling rate. If the current temperature reaches the stopping condition, the new solution is output and used as the population after the position of each individual is updated.

6. The method according to claim 1, characterized in that The randomly generated initialization population includes: In the search space, the initialization population is generated using Logistic chaotic mapping.

7. A reservoir optimization scheduling device based on the improved Pied Kingfisher algorithm, characterized in that: The device comprises: A construction module is used to construct a reservoir optimization scheduling model; wherein the reservoir optimization scheduling model uses the water level of the hydropower station in each period within the reservoir scheduling period as a decision variable; A generation module is used to randomly generate an initialization population; wherein the individuals in the initialization population represent the water level of the hydropower station in each period within the reservoir scheduling period; an iterative updating module, configured to iteratively update the position of each individual in the initialized population by simulating the perching and hovering behavior, diving behavior, and changes in predation efficiency of the pied kingfisher; The determination module is used to determine the optimal reservoir scheduling plan based on the iteratively updated population when the iteratively updated population meets the iteration stopping condition.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the reservoir optimization scheduling method based on the improved Pied Kingfisher algorithm according to any one of claims 1 to 6.

Images