Method and device for optimizing dispatching of hydropower station based on improved multi-objective dung beetle algorithm
By improving the multi-objective dung algorithm and fractional calculus technology, the problem of single and inaccurate optimization results in hydropower station optimization scheduling is solved, the power generation efficiency and system stability are improved, and management costs are reduced.
Patent Information
- Application Number
- CN202411067285.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-06
AI Technical Summary
Existing hydropower station optimization scheduling methods usually convert multi-objective problems into single-objective multi-constraint forms, resulting in a single solution and inaccurate optimization results.
Using the improved multi-objective dung beetle algorithm, a multi-objective scheduling model is constructed by obtaining the historical operation data of the hydropower station, and the dung beetle optimization algorithm is improved through fractional calculus. The improved algorithm is used to solve the multi-objective scheduling model of the hydropower station to obtain the optimized scheduling scheme. .
It significantly improves the power generation efficiency of hydropower stations, reduces water resource consumption, enhances system stability, reduces management costs, and provides scientific support for management decisions.
Smart Images

Figure CN118627844B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of hydropower station optimization dispatching, and in particular to a hydropower station optimization dispatching method and device based on an improved multi-objective dung beetle algorithm. Background Art
[0002] Reservoir optimization dispatching needs to comprehensively consider the power generation benefits of the entire reservoir as well as the ecological water demand and irrigation water guarantee needs. It is a complex, high-dimensional, dynamic and nonlinear multi-objective and multi-constraint problem. In recent years, some relatively mature intelligent algorithms have been widely used in hydropower station optimization dispatching and similar workshop dispatching, such as genetic algorithms, particle swarm algorithms and ant colony algorithms. However, these methods usually transform multi-objective problems into single-objective multi-constraint forms, and then use single-objective optimization algorithms to solve them. There are many defects and limitations such as single solution and inaccurate optimization results.
[0003] It can be seen that how to solve the current problem of single solution for optimal scheduling of hydropower stations and inaccurate optimization results has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention
[0004] The invention provides a method and device for optimizing the dispatching of a hydropower station based on an improved multi-objective dung beetle algorithm, which solves the current problems of single optimization solution and inaccurate optimization results for optimizing the dispatching of a hydropower station.
[0005] In order to solve the above technical problems, the first aspect of the present invention provides a hydropower station optimization scheduling method based on an improved multi-objective dung beetle algorithm, comprising:
[0006] Acquire historical operation data of the hydropower station, and construct a multi-objective dispatching model of the hydropower station based on the historical operation data;
[0007] The dung beetle optimization algorithm is improved by fractional calculus, and the improved multi-objective dung beetle algorithm is obtained.
[0008] The multi-objective dispatching model of the hydropower station is solved by the improved multi-objective dung beetle algorithm to obtain an optimized dispatching plan for the hydropower station.
[0009] As one of the preferred solutions, the multi-objective scheduling model of the hydropower station is expressed by the following formula:
[0010]
[0011]
[0012] In the formula, E is the power generation; T is the total number of dispatch periods; is the total output of the hydropower station at time t; ∆t is the time period granularity; W is the water consumption; is the water head of the hydropower station at time t; It is the water consumption of the hydropower station when the water head is H and the output is P at time t.
[0013] As one of the preferred solutions, the improvement of the dung beetle optimization algorithm by fractional calculus includes:
[0014] Construct fractional calculus expressions based on GL definitions;
[0015] Substitute the fractional calculus expression into the position update formula of the dung beetle optimization algorithm to improve the dung beetle optimization algorithm.
[0016] As one of the preferred solutions, the position update formula of the improved multi-target dung beetle algorithm includes the following formula:
[0017]
[0018] In the formula, is the updated position information of the i-th dung beetle at the r-th iteration; is the order; f(xn) is the nth order reciprocal of function f(x), n is a positive integer; is the position information of the i-th dung beetle at the r-th iteration; is the global worst position; is the position information of the i-th dung beetle at the r-1th iteration; is the natural coefficient.
[0019] As one of the preferred solutions, the improved multi-objective dung beetle algorithm includes:
[0020] Initializing the dung beetle population and parameters, calculating the fitness value of each dung beetle, and selecting a non-dominated solution set from the initialized dung beetle population according to the Pareto optimal solution sorting algorithm, calculating the non-dominated distance of the solution set in the non-dominated solution set and sorting them; the parameters include the number of iterations;
[0021] Finding an optimal solution set from the sorted non-dominated solution set, and updating the position information of dung beetles according to the position update formula of the dung beetle optimization algorithm or the position update formula of the improved multi-objective dung beetle algorithm to obtain a new dung beetle population; the optimal solution set includes a global optimal solution and a local optimal solution;
[0022] Introducing a hydropower station reservoir constraint to constrain the optimal solution set, selecting non-dominated solutions from the new dung beetle population and storing them in the non-dominated solution set to obtain a latest non-dominated solution set, calculating the crowding distance of the latest non-dominated solution set and sorting them, selecting a number of target non-dominated solutions from the sorted latest non-dominated solution set, and updating the optimal solution set according to the target non-dominated solutions;
[0023] Determine whether the number of iterations reaches the iteration number requirement. If not, repeat the updating of the position information of the dung beetles and the steps of selecting a number of target non-dominated solutions from the new dung beetle population until the number of iterations reaches the iteration number requirement, and output the updated optimal solution set obtained in the current iteration process.
[0024] A second aspect of the present invention provides a hydropower station optimization dispatching device based on an improved multi-objective dung beetle algorithm, comprising:
[0025] A model building module, used to obtain historical operation data of the hydropower station and build a multi-objective scheduling model of the hydropower station based on the historical operation data;
[0026] An algorithm improvement module is used to improve the dung beetle optimization algorithm through fractional calculus to obtain an improved multi-objective dung beetle algorithm;
[0027] The model solving module is used to solve the multi-objective scheduling model of the hydropower station through the improved multi-objective dung beetle algorithm to obtain the optimized scheduling plan of the hydropower station.
[0028] As one of the preferred solutions, the multi-objective scheduling model of the hydropower station is expressed by the following formula:
[0029]
[0030]
[0031] In the formula, E is the power generation; T is the total number of dispatch periods; is the total output of the hydropower station at time t; ∆t is the time period granularity; W is the water consumption; is the water head of the hydropower station at time t; It is the water consumption of the hydropower station when the water head is H and the output is P at time t.
[0032] As one of the preferred solutions, the improvement of the dung beetle optimization algorithm by fractional calculus includes:
[0033] Construct fractional calculus expressions based on GL definitions;
[0034] Substitute the fractional calculus expression into the position update formula of the dung beetle optimization algorithm to improve the dung beetle optimization algorithm.
[0035] As one of the preferred solutions, the position update formula of the improved multi-target dung beetle algorithm includes the following formula:
[0036]
[0037] In the formula, is the updated position information of the i-th dung beetle at the r-th iteration; is the order; f(xn) is the nth order reciprocal of function f(x), n is a positive integer; is the position information of the i-th dung beetle at the r-th iteration; is the global worst position; is the position information of the i-th dung beetle at the r-1th iteration; is the natural coefficient.
[0038] As one of the preferred solutions, the improved multi-objective dung beetle algorithm includes:
[0039] Initializing the dung beetle population and parameters, calculating the fitness value of each dung beetle, and selecting a non-dominated solution set from the initialized dung beetle population according to the Pareto optimal solution sorting algorithm, calculating the non-dominated distance of the solution set in the non-dominated solution set and sorting them; the parameters include the number of iterations;
[0040] Finding an optimal solution set from the sorted non-dominated solution set, and updating the position information of dung beetles according to the position update formula of the dung beetle optimization algorithm or the position update formula of the improved multi-objective dung beetle algorithm to obtain a new dung beetle population; the optimal solution set includes a global optimal solution and a local optimal solution;
[0041] Introducing a hydropower station reservoir constraint to constrain the optimal solution set, selecting non-dominated solutions from the new dung beetle population and storing them in the non-dominated solution set to obtain a latest non-dominated solution set, calculating the crowding distance of the latest non-dominated solution set and sorting them, selecting a number of target non-dominated solutions from the sorted latest non-dominated solution set, and updating the optimal solution set according to the target non-dominated solutions;
[0042] Determine whether the number of iterations reaches the iteration number requirement. If not, repeat the updating of the position information of the dung beetles and the steps of selecting a number of target non-dominated solutions from the new dung beetle population until the number of iterations reaches the iteration number requirement, and output the updated optimal solution set obtained in the current iteration process.
[0043] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0044] The present application establishes a mathematical model for optimizing the scheduling of a hydropower station with the maximum reservoir power generation and the minimum water consumption based on the historical operating data of the hydropower station, which can significantly improve the power generation efficiency of the hydropower station, reduce water resource consumption, enhance system stability, improve economic benefits, and provide scientific support for management decisions; in view of the complex, high-dimensional, dynamic and nonlinear characteristics of the target mathematical model, fractional-order calculus is substituted into the position update formula of the original dung beetle optimization algorithm, and the heredity and memory of fractional-order calculus are used to improve the problem that the original dung beetle is prone to falling into local optimality, and the convergence speed of the dung beetle algorithm can be effectively improved; using the improved multi-objective dung beetle algorithm to optimize the scheduling of the hydropower station, it is possible to optimize the operating efficiency of the hydropower station, improve the energy utilization rate and system stability in the hydropower station, and reduce management costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0046] Figure 1 It is a flow chart of a method for optimizing the dispatching of a hydropower station based on an improved multi-objective dung beetle algorithm provided by a certain embodiment of the present invention;
[0047] Figure 2 is a flow chart of a Pareto optimal solution sorting mechanism provided by an embodiment of the present invention;
[0048] Figure 3 is a flow chart of an improved multi-objective dung beetle algorithm provided by a certain embodiment of the present invention;
[0049] Figure 4 This is a simulation effect diagram of a fractional-order dung beetle algorithm provided by a certain embodiment of the present invention;
[0050] Figure 5 This is a simulation effect diagram of a dung beetle algorithm provided by a certain embodiment of the present invention;
[0051] Figure 6 It is a simulation effect diagram of a particle swarm algorithm provided by a certain embodiment of the present invention;
[0052] Figure 7 It is a structural diagram of a hydropower station optimization dispatching device based on an improved multi-objective dung beetle algorithm provided by a certain embodiment of the present invention. DETAILED DESCRIPTION
[0053] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0054] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.
[0055] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0056] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.
[0057] In one embodiment, if Figure 1 As shown, the first aspect of the present invention provides a hydropower station optimization scheduling method based on an improved multi-objective dung beetle algorithm, comprising:
[0058] S1. Obtain the historical operation data of the hydropower station, and construct a multi-objective scheduling model of the hydropower station based on the historical operation data; wherein the historical operation data includes the upstream water level storage capacity curve of the hydropower station, the downstream flow-water level curve, the full characteristic curve of the hydropower station, pressure, equipment status, power generation, power consumption, etc. This application collects and processes the historical operation data of the hydropower station - removes outliers and missing values, standardizes or normalizes the data, takes maximum power generation and minimum water consumption as the objective function, and adds the reservoir constraints of the hydropower station to construct a multi-objective scheduling model of the hydropower station.
[0059] In one embodiment, the multi-objective scheduling model of the hydropower station is expressed by the following formula:
[0060]
[0061]
[0062] In the formula, E is the power generation; T is the total number of dispatch periods; is the total output of the hydropower station at time t; ∆t is the time period granularity; W is the water consumption; is the water head of the hydropower station at time t; It is the water consumption of the hydropower station when the water head is H and the output is P at time t.
[0063] Among them, the reservoir constraints of the hydropower station include output constraints, reservoir water level constraints and power generation constraints, which are expressed by the following formula:
[0064]
[0065]
[0066]
[0067] In the formula, , are the minimum and maximum output of the turbine respectively; , are the lowest and highest water levels of the reservoir respectively; is the power generation of the hydropower station at time t; , are the minimum and maximum power generation of the turbine respectively.
[0068] This application establishes an optimal scheduling mathematical model for maximizing reservoir power generation and minimizing water consumption based on the historical operating data of the hydropower station. The model has strong adaptability and scalability, can significantly improve the power generation efficiency of the hydropower station, reduce water resource consumption, enhance system stability, improve economic benefits, and provide scientific support for management decisions, thereby jointly promoting the sustainable development and long-term operational benefits of the hydropower station.
[0069] S2. Improve the dung beetle optimization algorithm through fractional calculus to obtain an improved multi-objective dung beetle algorithm, which can also be called the fractional-order dung beetle algorithm;
[0070] In one embodiment, the improvement of the dung beetle optimization algorithm through fractional calculus includes:
[0071] Construct a fractional calculus expression based on the G-L definition; specifically, fractional calculus is the integration and differentiation with fractional orders, which is an extension of traditional calculus. In this application, the commonly used G-L (Grumwald-Letniko) definition of fractional calculus is adopted. Assuming that there is a continuously differentiable function in the interval [p, q] (p < q, and both are real numbers), then the first derivative of f(x) is:
[0072]
[0073] In the formula, is the increment on the interval [p, q]. Further derivation from the above formula gives the nth derivative of the function f(x) as:
[0074]
[0075] In the formula, n is a positive integer. Extend the order of the above formula from integer order to fractional order. When the order > 0, the order fractional-order expression defined by G-L is:
[0076]
[0077]
[0078] In the formula, is the Gamma function.
[0079] According to the above formula, the fractional calculus expression of the order integral of the signal f(x) defined by G-L can be obtained:
[0080]
[0081] In the formula, f(x - n) is the nth reciprocal of the function f(x).
[0082] Substitute the fractional-order calculus expression into the position update formula of the dung beetle optimization algorithm to improve the dung beetle optimization algorithm; specifically, in order to improve the global search capability, the present application introduces a fractional-order strategy into the dung beetle optimization algorithm, that is, substitutes the fractional-order calculus expression into the position update formula of the original dung beetle algorithm to improve the problem that the original dung beetle is prone to fall into the local optimum. The position update formula of the improved multi-objective dung beetle algorithm includes the following formula:
[0083]
[0084] In the formula, is the updated position information of the i-th dung beetle at the r-th iteration; For the order; is the position information of the i-th dung beetle at the r-th iteration; is the global worst position; is the position information of the i-th dung beetle at the r-1th iteration; is a natural coefficient, indicating whether it deviates from the original direction, and is assigned to −1 or 1 according to the probability method.
[0085] This application substitutes fractional-order calculus into the position update formula of the original dung beetle optimization algorithm, so that it serves as a fractional-order rolling ball dung beetle position update formula to replace the rolling ball dung beetle position update formula in the traditional dung beetle algorithm, so as to utilize the heredity and memory of fractional-order calculus to improve the problem that the original dung beetle is prone to falling into local optimality, and can effectively improve the convergence speed of the dung beetle algorithm.
[0086] The dung beetle optimization algorithm is a swarm intelligence optimization algorithm based on biological behavior. It is inspired by the behavioral characteristics of dung beetles in the process of foraging. This algorithm simulates the behavior of dung beetles leaving scents when looking for food, finding food sources by sensing these scents, and their habit of using the position of the sun to navigate and ensure that they always move in the direction of food. The dung beetle optimization algorithm also includes a deeper simulation of dung beetle behavior, such as rolling, dancing, foraging, stealing, and reproduction. These behaviors are converted into different dung beetle roles in the algorithm, such as rolling dung beetles, brooding balls, small dung beetles, and thief dung beetles. Each role has its own specific position update method; among them, the position update formula of the rolling dung beetle is:
[0087]
[0088] Where r is the current iteration number; k∈(0,0.2) represents the deflection coefficient; b∈(0,1) represents a constant; k and b are set to 0.1 and 0.3 respectively.
[0089] When a dung beetle dances (simulated using the tangent function), the position update formula is:
[0090]
[0091] In the formula, is an angle randomly selected in the interval [0, π] by the tangent function, which is used to determine the new moving direction.
[0092] When a dung beetle lays eggs (using a boundary selection strategy to simulate the egg-laying area), the update domain of the dung beetle egg-laying is:
[0093]
[0094]
[0095] In the formula, is the current global best position; and are the lower and upper limits of the spawning area, respectively; and are the lower and upper bounds of the optimization problem respectively; =1−r / r * , r * is the maximum number of iterations.
[0096] When the dung beetle spawning position is updated, the iterative update formula of the dung beetle position is:
[0097]
[0098] Where b1 and b2 are two independent random vectors of size 1×D, and D represents the dimension of the optimization problem.
[0099] The position update domain of the small dung beetle (i.e. the population of dung beetles when they are foraging) is:
[0100]
[0101]
[0102] In the formula, is the current global best position; and are the lower and upper limits of the optimal foraging area, respectively.
[0103] The iterative update formula of the dung beetle position is:
[0104]
[0105] Where C1 is a random number that follows a normal distribution; C2 is a random number between (0,1).
[0106] The iterative update formula of the position of the thief dung beetle is:
[0107]
[0108] Where g is a random vector of size 1×D that follows a normal distribution; S is a constant.
[0109] In one embodiment, the improved multi-objective dung beetle algorithm includes:
[0110] Initializing the dung beetle population and parameters, calculating the fitness value of each dung beetle, and selecting a non-dominated solution set from the initialized dung beetle population according to the Pareto optimal solution sorting algorithm, calculating the non-dominated distance of the solution set in the non-dominated solution set and sorting them; the parameters include the number of iterations;
[0111] Finding an optimal solution set from the sorted non-dominated solution set, and updating the position information of dung beetles according to the position update formula of the dung beetle optimization algorithm or the position update formula of the improved multi-objective dung beetle algorithm to obtain a new dung beetle population; the optimal solution set includes a global optimal solution and a local optimal solution;
[0112] Introducing a hydropower station reservoir constraint to constrain the optimal solution set, selecting non-dominated solutions from the new dung beetle population and storing them in the non-dominated solution set to obtain a latest non-dominated solution set, calculating the crowding distance of the latest non-dominated solution set and sorting them, selecting a number of target non-dominated solutions from the sorted latest non-dominated solution set, and updating the optimal solution set according to the target non-dominated solutions;
[0113] Determine whether the number of iterations reaches the iteration number requirement, if not, repeat the steps of updating the position information of the dung beetles and selecting a number of target non-dominated solutions from the new dung beetle population until the number of iterations reaches the iteration number requirement, and output the updated optimal solution set obtained in the current iteration process;
[0114] If so, the updated optimal solution set is directly output.
[0115] Specifically, the improved multi-objective dung beetle algorithm follows the following steps and strategies:
[0116] First, the dung beetle population is initialized. Each dung beetle individual represents a potential solution, including parameters such as unit output and reservoir flow, and the algorithm parameters are set, including population size, number of iterations, population dimension, etc. Then, the objective function - the multi-objective scheduling model of the hydropower station is used to calculate the fitness value of each dung beetle individual, evaluate its advantages and disadvantages, and select the non-dominated solution set from the population through the Pareto optimal solution sorting algorithm. The Pareto optimal solution sorting mechanism process is as follows Figure 2As shown in the figure: through the dominance relationship between dung beetle individuals, the individuals are divided into unequal non-dominated levels using fast non-dominated sorting, and the non-dominated solution set of the current dung beetle population is composed of individuals at the first level; the crowding distance operator is then used to calculate the crowding distance between individuals in different non-dominated levels, and then the individuals are sorted again according to the size of the crowding distance; after the above two operator operations are completed, the individuals are finally divided into different sets according to the different non-dominated levels, and the individuals in the sets are sorted in descending order according to the size of the crowding distance. After the sorting is completed, the non-dominated solution set of the current dung beetle population will be stored in the external archive set A, and the last N with the largest non-dominated level and the smallest crowding distance d Individuals will be eliminated to form a non-dominated solution set A.
[0117] Then the crowding distance of the non-dominated solution set A is calculated and sorted, and the optimal solution set including the global optimal solution and the local optimal solution is found in the sorted non-dominated solution set, and the position and speed of the dung beetle in the global optimal solution set are updated by the position update formula to obtain a new population. Then the reservoir constraint of the hydropower station is introduced to limit the position of the dung beetle, and then a new non-dominated solution (i.e., a new potential solution) is selected from the new population and stored in the non-dominated solution set to obtain the latest non-dominated solution set. The crowding distance of the latest non-dominated solution set is calculated and sorted, and the first n non-dominated solutions are selected from the latest sorted non-dominated solution set and added to the optimal solution set, and the number of iterations is judged. When it does not exceed the preset number of iterations, the iterative process is started, that is, the updating process of the iterative dung beetle population and the latest non-dominated solution set, until the preset number of iterations is reached or other termination conditions (such as fitness value convergence) are met, and the global optimal solution in the optimal solution set is output, that is, the optimal hydropower station scheduling plan and its corresponding objective function value are finally obtained.
[0118] Among them, the improved multi-objective dung beetle algorithm process is as follows Figure 3As shown in FIG. 1 , in each iteration process, the position update formula used is different according to the number of iterations. When the number of iterations is not more than 3, the position update formula of the rolling ball dung beetle, dung beetle egg laying, small dung beetle, and thief dung beetle in the original dung beetle optimization algorithm is used to update the position information of the dung beetles in the population. When the number of iterations is more than 3, the fractional order rolling ball dung beetle position update formula of the improved multi-objective dung beetle algorithm is used to replace the rolling ball dung beetle position update formula in the original dung beetle optimization algorithm. Then, the dung beetle egg laying, small dung beetle, and thief dung beetle in the original dung beetle optimization algorithm are used to update the position information of the dung beetles in the population. The position update formula of dung beetles is used to update the position information of dung beetles in the population, that is, the position update formula of the improved multi-objective dung beetle algorithm includes the fractional rolling ball dung beetle position update formula and the position update formula of dung beetle egg laying, small dung beetles, and thief dung beetles in the traditional original dung beetle optimization algorithm. Through the above method, the position of dung beetles (that is, the hydropower station scheduling plan) is continuously adjusted to gradually approach the optimal solution. This iterative optimization process combines the biological characteristics of dung beetles and the actual needs of hydropower station scheduling, so that the algorithm can effectively solve the problem of hydropower station optimization scheduling. It should be noted that the preset values used in this article can be experimentally adjusted according to actual needs, and no specific numerical limit is made here.
[0119] S3. Solve the multi-objective scheduling model of the hydropower station by using the improved multi-objective dung beetle algorithm to obtain an optimized scheduling plan for the hydropower station; specifically, input the global optimal solution obtained by the improved multi-objective dung beetle algorithm into the multi-objective scheduling model of the hydropower station to obtain an optimized scheduling plan including output data and water consumption data.
[0120] In order to verify the effectiveness of the improved multi-objective dung beetle algorithm in this application in hydropower optimization scheduling, experimental simulation is carried out on a specific hydropower station, and a comparative analysis is conducted with the particle swarm algorithm (Genetic Algorithm, GA) and the dung beetle algorithm (DBO). The initial population size is set to 30, the maximum number of iterations is set to 300, and 20 experiments are used to avoid randomness and systematic errors of the algorithm and the average is taken as the experimental result. The parameters of the hydropower station are as follows:
[0121]
[0122] Based on the parameters of the above hydropower station, the multi-objective scheduling model of the hydropower station is used to carry out experimental simulation, that is, the maximum power generation and the minimum water consumption are used as the objective function, and the initial water level of the hydropower station is set to 27.6m. According to the water level-reservoir capacity curve, the reservoir capacity of the hydropower station is 15.9*10^6m 3 , set the daily average water flow to 589 m 3 / s, simulate the hydropower station; the simulation effect of the fractional order dung beetle algorithm is shown in the figure Figure 4As shown in the figure, the simulation effect of the dung beetle algorithm is as follows Figure 5 As shown in the figure, the simulation effect of particle swarm algorithm is as follows Figure 6 For specific data comparison, please refer to the following table:
[0123]
[0124] From the comparison in the table, we can see that the difference between the water consumption rate of the dung beetle algorithm and the particle swarm algorithm is not much, only 0.002m 3 / MW, the water consumption rate of the improved multi-objective dung beetle algorithm is reduced by 0.344m compared with the ordinary dung beetle algorithm. 3 / MW, with remarkable results. It can be seen that the application uses the improved multi-objective dung beetle algorithm to optimize the scheduling of hydropower stations, which can more effectively utilize water resources to generate electricity and improve the efficiency of water resource utilization.
[0125] In the embodiment of the present application, based on the current problem of single solution and inaccurate optimization results for the optimization scheduling of hydropower stations, a method for optimizing the scheduling of hydropower stations based on an improved multi-objective dung beetle algorithm is designed, which realizes the acquisition of historical operation data of the hydropower station and constructs a multi-objective scheduling model of the hydropower station according to the historical operation data; the dung beetle optimization algorithm is improved by fractional calculus to obtain an improved multi-objective dung beetle algorithm; the multi-objective scheduling model of the hydropower station is solved by the improved multi-objective dung beetle algorithm to obtain a technical solution for the optimization scheduling scheme of the hydropower station; the present application introduces the concept of fractional order into the original dung beetle optimization algorithm to solve the scheduling scheme of the hydropower station, which can effectively avoid falling into a local optimal solution, optimize the operating efficiency of the hydropower station, and at the same time reduce management costs and improve management efficiency.
[0126] It should be noted that although the steps in the above flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders.
[0127] In another embodiment, if Figure 7 As shown, the second aspect of the present invention provides a hydropower station optimization scheduling device based on an improved multi-objective dung beetle algorithm, comprising:
[0128] The model building module 10 is used to obtain the historical operation data of the hydropower station and build a multi-objective scheduling model of the hydropower station based on the historical operation data; wherein the historical operation data includes the upstream water level storage capacity curve of the hydropower station, the downstream flow-water level curve, the full characteristic curve of the hydropower station, pressure, equipment status, power generation, power consumption, etc. The present application collects and processes the historical operation data of the hydropower station - removes outliers and missing values, standardizes or normalizes the data, takes maximum power generation and minimum water consumption as the objective function, and adds the reservoir constraints of the hydropower station to build a multi-objective scheduling model of the hydropower station.
[0129] In one embodiment, the multi-objective scheduling model of the hydropower station is expressed by the following formula:
[0130]
[0131]
[0132] In the formula, E is the power generation; T is the total number of dispatch periods; is the total output of the hydropower station at time t; ∆t is the time period granularity; W is the water consumption; is the water head of the hydropower station at time t; It is the water consumption of the hydropower station when the water head is H and the output is P at time t.
[0133] Among them, the reservoir constraints of the hydropower station include output constraints, reservoir water level constraints and power generation constraints, which are expressed by the following formula:
[0134]
[0135]
[0136]
[0137] In the formula, , are the minimum and maximum output of the turbine respectively; , are the lowest and highest water levels of the reservoir respectively; is the power generation of the hydropower station at time t; , are the minimum and maximum power generation of the turbine respectively.
[0138] This application establishes an optimal scheduling mathematical model for maximizing reservoir power generation and minimizing water consumption based on the historical operating data of the hydropower station. The model has strong adaptability and scalability, can significantly improve the power generation efficiency of the hydropower station, reduce water resource consumption, enhance system stability, improve economic benefits, and provide scientific support for management decisions, thereby jointly promoting the sustainable development and long-term operational benefits of the hydropower station.
[0139] The algorithm improvement module 20 is used to improve the dung beetle optimization algorithm through fractional calculus to obtain an improved multi-objective dung beetle algorithm;
[0140] In one embodiment, the improvement of the dung beetle optimization algorithm through fractional calculus includes:
[0141] Construct a fractional calculus expression based on the G-L definition; specifically, fractional calculus is the integration and differentiation of fractional order, which is an extension of traditional calculus. In this application, the commonly used G-L (Grumwald-Letniko) definition of fractional calculus is adopted. Assuming that there is a continuously differentiable function in the interval [a, b] (a < b, and both are real numbers), the first derivative of f(x) is:
[0142]
[0143] In the formula, is the increment on the interval [a, b]. Further derivation from the above formula gives the nth derivative of the function f(x) as:
[0144]
[0145] In the formula, n is a positive integer. Extend the order of the above formula from integer order to fractional order. When the order > 0, the order fractional order expression defined by G-L is:
[0146]
[0147]
[0148] In the formula, is the Gamma function.
[0149] According to the above formula, the fractional calculus expression of the order integral of the signal f(x) defined by G-L can be obtained:
[0150]
[0151] In the formula, f(x - n) is the nth reciprocal of the function f(x).
[0152] Substitute the fractional calculus expression into the position update formula of the dung beetle optimization algorithm to improve the dung beetle optimization algorithm; specifically, in order to improve the global search ability, this application introduces a fractional order strategy into the dung beetle optimization algorithm, that is, substituting the fractional calculus expression into the position update formula of the original dung beetle algorithm to improve the problem that the original dung beetle is prone to falling into local optimum. The position update formula of the improved multi-objective dung beetle algorithm includes the following formula:
[0153]
[0154] In the formula, is the updated position information of the i-th dung beetle at the r-th iteration; For the order; is the position information of the i-th dung beetle at the r-th iteration; is the global worst position; is the position information of the i-th dung beetle at the r-1th iteration; is a natural coefficient, indicating whether it deviates from the original direction, and is assigned to −1 or 1 according to the probability method.
[0155] This application substitutes fractional-order calculus into the position update formula of the original dung beetle optimization algorithm, so that it serves as a fractional-order rolling ball dung beetle position update formula to replace the rolling ball dung beetle position update formula in the traditional dung beetle algorithm, so as to utilize the heredity and memory of fractional-order calculus to improve the problem that the original dung beetle is prone to falling into local optimality, and can effectively improve the convergence speed of the dung beetle algorithm.
[0156] The dung beetle optimization algorithm is a swarm intelligence optimization algorithm based on biological behavior, inspired by the behavioral characteristics of dung beetles in the process of foraging. This algorithm simulates the behavior of dung beetles leaving scents when looking for food, finding food sources by sensing these scents, and their habit of using the position of the sun to navigate and ensure that they always move in the direction of food. The dung beetle optimization algorithm also includes a deeper simulation of dung beetle behavior, such as rolling, dancing, foraging, stealing, and breeding behaviors. These behaviors are converted into different dung beetle roles in the algorithm, such as rolling ball dung beetles, brooding balls, small dung beetles, and thief dung beetles. Each role has its own specific position update method; among them, the position update formula of the rolling ball dung beetle is:
[0157]
[0158] Where r is the current iteration number; k∈(0,0.2) represents the deflection coefficient; b∈(0,1) represents a constant; k and b are set to 0.1 and 0.3 respectively.
[0159] When a dung beetle dances (simulated using the tangent function), the position update formula is:
[0160]
[0161] In the formula, is an angle randomly selected in the interval [0, π] by the tangent function, which is used to determine the new moving direction.
[0162] When a dung beetle lays eggs (using a boundary selection strategy to simulate the egg-laying area), the update domain of the dung beetle egg-laying is:
[0163]
[0164]
[0165] In the formula, is the current global best position; and are the lower and upper limits of the spawning area, respectively; and are the lower and upper bounds of the optimization problem respectively; =1−r / r * , r * is the maximum number of iterations.
[0166] When the dung beetle spawning position is updated, the iterative update formula of the dung beetle position is:
[0167]
[0168] Where b1 and b2 are two independent random vectors of size 1×D, and D represents the dimension of the optimization problem.
[0169] The position update domain of the small dung beetle (i.e. the population of dung beetles when they are foraging) is:
[0170]
[0171]
[0172] In the formula, is the current global best position; and are the lower and upper limits of the optimal foraging area, respectively.
[0173] The iterative update formula of the dung beetle position is:
[0174]
[0175] Where C1 is a random number that follows a normal distribution; C2 is a random number between (0,1).
[0176] The iterative update formula of the position of the thief dung beetle is:
[0177]
[0178] Where g is a random vector of size 1×D that follows a normal distribution; S is a constant.
[0179] In one embodiment, the improved multi-objective dung beetle algorithm includes:
[0180] Initializing the dung beetle population and parameters, calculating the fitness value of each dung beetle, and selecting a non-dominated solution set from the initialized dung beetle population according to the Pareto optimal solution sorting algorithm, calculating the non-dominated distance of the solution set in the non-dominated solution set and sorting them; the parameters include the number of iterations;
[0181] Finding an optimal solution set from the sorted non-dominated solution set, and updating the position information of dung beetles according to the position update formula of the dung beetle optimization algorithm or the position update formula of the improved multi-objective dung beetle algorithm to obtain a new dung beetle population; the optimal solution set includes a global optimal solution and a local optimal solution;
[0182] Introducing a hydropower station reservoir constraint to constrain the optimal solution set, selecting non-dominated solutions from the new dung beetle population and storing them in the non-dominated solution set to obtain a latest non-dominated solution set, calculating the crowding distance of the latest non-dominated solution set and sorting them, selecting a number of target non-dominated solutions from the sorted latest non-dominated solution set, and updating the optimal solution set according to the target non-dominated solutions;
[0183] Determine whether the number of iterations reaches the iteration number requirement, if not, repeat the steps of updating the position information of the dung beetles and selecting a number of target non-dominated solutions from the new dung beetle population until the number of iterations reaches the iteration number requirement, and output the updated optimal solution set obtained in the current iteration process;
[0184] If so, the updated optimal solution set is directly output.
[0185] Specifically, the improved multi-objective dung beetle algorithm follows the following steps and strategies:
[0186] First, the dung beetle population is initialized, and each dung beetle individual represents a potential solution, including parameters such as unit output and reservoir flow, and the algorithm parameters are set, including population size, number of iterations, population dimension, etc.; then the objective function-hydropower station multi-objective scheduling model is used to calculate the fitness value of each dung beetle individual, evaluate its advantages and disadvantages, and select the non-dominated solution set from the population through the Pareto optimal solution sorting algorithm: through the dominance relationship between dung beetle individuals, the individuals are divided into unequal non-dominated levels using fast non-dominated sorting, and the non-dominated solution set of the current dung beetle population is composed of individuals in the first level; then the crowding distance operator is used to calculate the crowding distance between individuals in different non-dominated levels, and then the individuals are sorted again according to the size of the crowding distance; after the above two operator operations are completed, the individuals are finally divided into different sets according to the different non-dominated levels, and the individuals in the sets are sorted in descending order according to the size of the crowding distance. After the sorting is completed, the non-dominated solution set of the current dung beetle population will be stored in the external archive set A, and the last N with the largest non-dominated level and the smallest crowding distance dIndividuals will be eliminated to form a non-dominated solution set A.
[0187] Then the crowding distance of the non-dominated solution set A is calculated and sorted, and the optimal solution set including the global optimal solution and the local optimal solution is found in the sorted non-dominated solution set, and the position and speed of the dung beetle in the global optimal solution set are updated by the position update formula to obtain a new population. Then the reservoir constraint of the hydropower station is introduced to limit the position of the dung beetle, and then a new non-dominated solution (i.e., a new potential solution) is selected from the new population and stored in the non-dominated solution set to obtain the latest non-dominated solution set. The crowding distance of the latest non-dominated solution set is calculated and sorted, and the first n non-dominated solutions are selected from the latest sorted non-dominated solution set and added to the optimal solution set, and the number of iterations is judged. When it does not exceed the preset number of iterations, the iterative process is started, that is, the updating process of the iterative dung beetle population and the latest non-dominated solution set, until the preset number of iterations is reached or other termination conditions (such as fitness value convergence) are met, and the global optimal solution in the optimal solution set is output, that is, the optimal hydropower station scheduling plan and its corresponding objective function value are finally obtained.
[0188] Among them, in each iteration process, according to the different number of iterations, the position update formula used is also different. When the number of iterations is not more than 3, the position update formula of rolling ball dung beetles, dung beetle egg laying, small dung beetles, and thief dung beetles in the original dung beetle optimization algorithm is used to update the position information of dung beetles in the population. When the number of iterations is greater than 3, the fractional order rolling ball dung beetle position update formula of the improved multi-objective dung beetle algorithm is used to replace the rolling ball dung beetle position update formula in the original dung beetle optimization algorithm, and then the dung beetle egg laying, small dung beetle, and thief dung beetle position update formula in the original dung beetle optimization algorithm are used. The position update formula of dung beetles is used to update the position information of dung beetles in the population, that is, the position update formula of the improved multi-objective dung beetle algorithm includes the fractional rolling ball dung beetle position update formula and the position update formula of dung beetle egg laying, small dung beetles, and thief dung beetles in the traditional original dung beetle optimization algorithm. Through the above method, the position of dung beetles (that is, the hydropower station scheduling plan) is continuously adjusted to gradually approach the optimal solution. This iterative optimization process combines the biological characteristics of dung beetles and the actual needs of hydropower station scheduling, so that the algorithm can effectively solve the problem of hydropower station optimization scheduling. It should be noted that the preset values used in this article can be experimentally adjusted according to actual needs, and no specific numerical limit is made here.
[0189] The model solving module 30 is used to solve the multi-objective scheduling model of the hydropower station through the improved multi-objective dung beetle algorithm to obtain the optimized scheduling plan of the hydropower station; specifically, the global optimal solution obtained by the improved multi-objective dung beetle algorithm is input into the multi-objective scheduling model of the hydropower station to obtain the optimized scheduling plan including output data and water consumption data.
[0190] It should be noted that each module in the above-mentioned hydropower station optimization dispatching device based on the improved multi-objective dung beetle algorithm can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0191] In summary, the present invention discloses a method and device for optimizing the scheduling of a hydropower station based on an improved multi-objective dung beetle algorithm, wherein the method comprises obtaining historical operating data of the hydropower station, and constructing a multi-objective scheduling model of the hydropower station according to the historical operating data; improving the dung beetle optimization algorithm by fractional-order calculus to obtain an improved multi-objective dung beetle algorithm; solving the multi-objective scheduling model of the hydropower station by the improved multi-objective dung beetle algorithm to obtain an optimized scheduling plan of the hydropower station; the present application introduces the concept of fractional order into the original dung beetle optimization algorithm to solve the scheduling plan of the hydropower station, which can effectively avoid falling into a local optimal solution, optimize the operating efficiency of the hydropower station, and at the same time reduce management costs and improve management efficiency.
[0192] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0193] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.
Claims
1. A hydropower station optimization scheduling method based on an improved multi-objective dung beetle algorithm, characterized in that: include: Acquire historical operation data of the hydropower station, and construct a multi-objective dispatching model of the hydropower station based on the historical operation data; The dung beetle optimization algorithm is improved by fractional calculus, and the improved multi-objective dung beetle algorithm is obtained. Solving the multi-objective dispatching model of the hydropower station by using the improved multi-objective dung beetle algorithm to obtain an optimized dispatching plan of the hydropower station; The improvement of the dung beetle optimization algorithm by fractional calculus includes: Construct fractional calculus expressions based on GL definitions; Substituting the fractional calculus expression into the position update formula of the dung beetle optimization algorithm to improve the dung beetle optimization algorithm; The position update formula of the improved multi-target dung beetle algorithm includes the following formula: In the formula, is the updated position information of the i-th dung beetle at the r-th iteration; is the order; f(xn) is the nth order reciprocal of function f(x), n is a positive integer; is the position information of the i-th dung beetle at the r-th iteration; is the global worst position; is the position information of the i-th dung beetle at the r-1th iteration; is the natural coefficient.
2. The method for optimizing the dispatching of a hydropower station based on an improved multi-objective dung beetle algorithm according to claim 1 is characterized in that: The multi-objective dispatching model of the hydropower station is expressed by the following formula: Where, E is the power generation; T is the total number of scheduling periods; is the total output of the hydropower station at time t; ∆t is the time period granularity; W is the water consumption; is the water head of the hydropower station at time t; It is the water consumption of the hydropower station when the water head is H and the output is P at time t.
3. The method for optimizing the dispatching of a hydropower station based on an improved multi-objective dung beetle algorithm according to claim 1 is characterized in that: The improved multi-objective dung beetle algorithm comprises: Initializing the dung beetle population and parameters, calculating the fitness value of each dung beetle, and selecting a non-dominated solution set from the initialized dung beetle population according to the Pareto optimal solution sorting algorithm, calculating the non-dominated distance of the solution set in the non-dominated solution set and sorting them; the parameters include the number of iterations; Finding an optimal solution set from the sorted non-dominated solution set, and updating the position information of dung beetles according to the position update formula of the improved multi-objective dung beetle algorithm to obtain a new dung beetle population; the optimal solution set includes a global optimal solution and a local optimal solution; Introducing a hydropower station reservoir constraint to constrain the optimal solution set, selecting non-dominated solutions from the new dung beetle population and storing them in the non-dominated solution set to obtain a latest non-dominated solution set, calculating the crowding distance of the latest non-dominated solution set and sorting them, selecting a number of target non-dominated solutions from the sorted latest non-dominated solution set, and updating the optimal solution set according to the target non-dominated solutions; Determine whether the number of iterations reaches the iteration number requirement. If not, repeat the updating of the position information of the dung beetles and the steps of selecting a number of target non-dominated solutions from the new dung beetle population until the number of iterations reaches the iteration number requirement, and output the updated optimal solution set obtained in the current iteration process.
4. A hydropower station optimization dispatching device based on an improved multi-objective dung beetle algorithm, characterized in that: include: A model building module, used to obtain historical operation data of the hydropower station and build a multi-objective scheduling model of the hydropower station based on the historical operation data; An algorithm improvement module is used to improve the dung beetle optimization algorithm through fractional calculus to obtain an improved multi-objective dung beetle algorithm; A model solving module, used for solving the multi-objective dispatching model of the hydropower station by using the improved multi-objective dung beetle algorithm to obtain an optimized dispatching plan of the hydropower station; The improvement of the dung beetle optimization algorithm by fractional calculus includes: Construct fractional calculus expressions based on GL definitions; Substituting the fractional calculus expression into the position update formula of the dung beetle optimization algorithm to improve the dung beetle optimization algorithm; The position update formula of the improved multi-target dung beetle algorithm includes the following formula: In the formula, is the updated position information of the i-th dung beetle at the r-th iteration; is the order; f(xn) is the nth order reciprocal of function f(x), n is a positive integer; is the position information of the i-th dung beetle at the r-th iteration; is the global worst position; is the position information of the i-th dung beetle at the r-1th iteration; is the natural coefficient.
5. The hydropower station optimization dispatching device based on the improved multi-objective dung beetle algorithm according to claim 4 is characterized in that: The multi-objective dispatching model of the hydropower station is expressed by the following formula: In the formula, E is the power generation; T is the total number of dispatch periods; is the total output of the hydropower station at time t; ∆t is the time period granularity; W is the water consumption; is the water head of the hydropower station at time t; It is the water consumption of the hydropower station when the water head is H and the output is P at time t.
6. The hydropower station optimization dispatching device based on the improved multi-objective dung beetle algorithm according to claim 4 is characterized in that: The improved multi-objective dung beetle algorithm comprises: Initializing the dung beetle population and parameters, calculating the fitness value of each dung beetle, and selecting a non-dominated solution set from the initialized dung beetle population according to the Pareto optimal solution sorting algorithm, calculating the non-dominated distance of the solution set in the non-dominated solution set and sorting them; the parameters include the number of iterations; Finding an optimal solution set from the sorted non-dominated solution set, and updating the position information of dung beetles according to the position update formula of the improved multi-objective dung beetle algorithm to obtain a new dung beetle population; the optimal solution set includes a global optimal solution and a local optimal solution; Introducing a hydropower station reservoir constraint to constrain the optimal solution set, selecting non-dominated solutions from the new dung beetle population and storing them in the non-dominated solution set to obtain a latest non-dominated solution set, calculating the crowding distance of the latest non-dominated solution set and sorting them, selecting a number of target non-dominated solutions from the sorted latest non-dominated solution set, and updating the optimal solution set according to the target non-dominated solutions; Determine whether the number of iterations reaches the iteration number requirement. If not, repeat the updating of the position information of the dung beetles and the steps of selecting a number of target non-dominated solutions from the new dung beetle population until the number of iterations reaches the iteration number requirement, and output the updated optimal solution set obtained in the current iteration process.
