Generation method and device of power dispatching scheme, equipment, storage medium and product

Abstract

The invention discloses a power dispatching scheme generation method and apparatus, a device, a storage medium and a product. The method comprises the steps of obtaining a to-be-dispatched power generation field and determining a mathematical model of the to-be-dispatched power generation field; according to the mathematical model of the to-be-dispatched power generation field, an initial dispatching scheme set of the to-be-dispatched power generation field is obtained in combination with a set algorithm; wherein the initial scheduling scheme set comprises at least one initial scheduling scheme; and in combination with an elitism strategy, screening the initial scheduling scheme set, and taking a screening result as a target scheduling scheme of the to-be-scheduled power generation field. According to the power dispatching scheme generation method disclosed by the invention, the initial dispatching scheme is obtained by using the algorithm, and the final target dispatching scheme is obtained by screening in combination with the elitism strategy, so that an optimal solution can be better found for a complex problem, and a better power dispatching scheme is obtained.

Description

Technical Field

[0001] The present invention relates to the field of power generation technology, and in particular to a method, device, equipment, storage medium and product for generating a power dispatching plan. Background Art

[0002] The environmental economic dispatch problem of power system is a typical non-convex, nonlinear, high-dimensional, multi-objective optimization problem with multiple constraints. The grid-connected wind power will increase the variables and constraints in the power system and make the model more complex.

[0003] In the prior art, for the multi-objective optimization scheduling problem of power plants, especially those including wind turbines, the constraints contained in the problem model are often limited when solving the problem. In addition, given the uncertainty of wind energy, it is particularly important to more accurately predict wind power output, and it is necessary to further improve the reliability of the power system after wind power is connected to the grid. The algorithms used in the prior art to solve this problem have problems in performance, such as being prone to falling into local optimality and insufficient population diversity. Summary of the invention

[0004] The present invention provides a method, device, equipment, storage medium and product for generating a power dispatching scheme to achieve optimized dispatching of a power plant.

[0005] According to one aspect of the present invention, a method for generating a power dispatching plan is provided, comprising:

[0006] Acquire a power plant to be scheduled and determine a mathematical model of the power plant to be scheduled;

[0007] According to the mathematical model of the power plant to be scheduled, combined with the set algorithm, an initial scheduling scheme set of the power plant to be scheduled is obtained; wherein the initial scheduling scheme set includes at least one initial scheduling scheme;

[0008] Combined with the elite retention strategy, the initial scheduling scheme set is screened, and the screening result is used as the target scheduling scheme of the power plant to be scheduled.

[0009] Furthermore, the power plant to be scheduled includes at least one wind turbine group.

[0010] Furthermore, according to the mathematical model of the power plant to be scheduled, combined with the set algorithm, an initial scheduling scheme set of the power plant to be scheduled is obtained, including:

[0011] Using a target hybrid frog leaping algorithm as the setting algorithm, and determining an objective function and constraint conditions of the target hybrid frog leaping algorithm according to a mathematical model of the power plant to be scheduled;

[0012] According to the target hybrid frog leaping algorithm, a first initialization population is randomly generated; wherein the first initialization population includes at least one individual, and each individual corresponds to a scheduling scheme;

[0013] Optimizing and updating each individual in the first initialized population to obtain an optimized new population;

[0014] The new population is used as an initial scheduling solution set for the power plant to be scheduled.

[0015] Furthermore, the objective function includes a power generation cost function and a pollution emission function.

[0016] Furthermore, each individual in the first initialized population is optimized and updated to obtain an optimized new population, including:

[0017] For each individual in the first initialized population, determine the crowding degree of each individual respectively;

[0018] Determine the worst individual in the first initialized population according to the crowding degree of each individual;

[0019] Randomly generate a new individual, and if the new individual is better than the worst individual, the new individual is used to replace the worst individual;

[0020] Return to the step of determining the worst individual in the first initialized population according to the crowding degree of each individual, until the set number of iterations is reached to obtain the new population.

[0021] Furthermore, in combination with the elite retention strategy, the initial scheduling solution set is screened, including:

[0022] According to the target hybrid frog leaping algorithm, a second initialization population is randomly generated; wherein the second initialization population includes at least one individual, and each individual corresponds to a scheduling scheme;

[0023] Using the initial scheduling solution set as a child population, and merging the child population with the second initialization population to obtain a new population;

[0024] For each individual in the new population, the crowding degree of each individual is determined and sorted respectively, and a set number of individuals in the new population are retained as the screening result in the order of crowding degree.

[0025] According to another aspect of the present invention, there is provided a device for generating a power dispatching plan, comprising:

[0026] A mathematical model determination module, used for acquiring a power plant to be scheduled and determining a mathematical model of the power plant to be scheduled;

[0027] An initial scheduling scheme set generation module is used to obtain an initial scheduling scheme set of the power plant to be scheduled according to the mathematical model of the power plant to be scheduled and in combination with a set algorithm; wherein the initial scheduling scheme set includes at least one initial scheduling scheme;

[0028] The target scheduling scheme determination module is used to screen the initial scheduling scheme set in combination with the elite retention strategy, and use the screening result as the target scheduling scheme of the power plant to be scheduled.

[0029] Optionally, the power plant to be scheduled includes at least one wind turbine.

[0030] Optionally, the initial scheduling solution set generation module is further used to:

[0031] Using a target hybrid frog leaping algorithm as the setting algorithm, and determining an objective function and constraint conditions of the target hybrid frog leaping algorithm according to a mathematical model of the power plant to be scheduled;

[0032] According to the target hybrid frog leaping algorithm, a first initialization population is randomly generated; wherein the first initialization population includes at least one individual, and each individual corresponds to a scheduling scheme;

[0033] Optimizing and updating each individual in the first initialized population to obtain an optimized new population;

[0034] The new population is used as an initial scheduling solution set for the power plant to be scheduled.

[0035] Optionally, the objective function includes a power generation cost function and a pollution emission function.

[0036] Optionally, the initial scheduling solution set generation module is further used to:

[0037] For each individual in the first initialized population, determine the crowding degree of each individual respectively;

[0038] Determine the worst individual in the first initialized population according to the crowding degree of each individual;

[0039] Randomly generate a new individual, and if the new individual is better than the worst individual, the new individual is used to replace the worst individual;

[0040] Return to the step of determining the worst individual in the first initialized population according to the crowding degree of each individual, until the set number of iterations is reached to obtain the new population.

[0041] Optionally, the target scheduling scheme determination module is further used to:

[0042] According to the target hybrid frog leaping algorithm, a second initialization population is randomly generated; wherein the second initialization population includes at least one individual, and each individual corresponds to a scheduling scheme;

[0043] Using the initial scheduling solution set as a child population, and merging the child population with the second initialization population to obtain a new population;

[0044] For each individual in the new population, the crowding degree of each individual is determined and sorted respectively, and a set number of individuals in the new population are retained as the screening result in the order of crowding degree.

[0045] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0046] at least one processor; and

[0047] a memory communicatively connected to the at least one processor; wherein,

[0048] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating a power dispatching plan described in any embodiment of the present invention.

[0049] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a power dispatching plan described in any embodiment of the present invention when executed.

[0050] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program / instructions, which, when executed by a processor, implement the steps of the method for generating a power dispatching scheme described in any embodiment of the present invention.

[0051] The method for generating a power dispatching scheme disclosed in the present invention first obtains the power plant to be dispatched and determines the mathematical model of the power plant to be dispatched; then, based on the mathematical model of the power plant to be dispatched and in combination with a set algorithm, an initial dispatching scheme set for the power plant to be dispatched is obtained; wherein the initial dispatching scheme set includes at least one initial dispatching scheme; finally, in combination with an elite retention strategy, the initial dispatching scheme set is screened, and the screening result is used as the target dispatching scheme for the power plant to be dispatched. The method for generating a power dispatching scheme disclosed in the present invention obtains the initial dispatching scheme by using an algorithm, and then obtains the final target dispatching scheme by screening in combination with an elite retention strategy, so that the optimal solution for complex problems can be better found, thereby obtaining a better power dispatching scheme.

[0052] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 is a flow chart of a method for generating a power dispatching plan according to Embodiment 1 of the present invention;

[0055] Figure 2 1 is a schematic diagram of an individual update process based on a hybrid frog leaping algorithm according to Embodiment 1 of the present invention;

[0056] Figure 3 is a schematic diagram of a population screening process based on an elite retention strategy provided according to Embodiment 1 of the present invention;

[0057] Figure 4 is a structural schematic diagram of a device for generating a power dispatching solution according to Embodiment 2 of the present invention;

[0058] Figure 5 It is a structural schematic diagram of an electronic device for implementing the method for generating a power dispatching plan according to the third embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0060] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0061] Embodiment 1

[0062] Figure 1 This is a flow chart of a method for generating a power dispatching plan provided in the first embodiment of the present invention. This embodiment is applicable to the case of optimizing the dispatching of power plants. The method can be executed by a device for generating a power dispatching plan. The device for generating a power dispatching plan can be implemented in the form of hardware and / or software. The device for generating a power dispatching plan can be configured in an electronic device. Figure 1 As shown, the method includes:

[0063] S110, obtaining a power plant to be dispatched and determining a mathematical model of the power plant to be dispatched.

[0064] The power plant to be dispatched includes at least one wind turbine.

[0065] In this embodiment, the environmental economic dispatch (EED) of the power system refers to effectively and reasonably deploying the contribution of each unit according to the load demand of the network at a specific time or a period of time to achieve the lowest pollution emission and the lowest economic cost. By performing environmental economic dispatch on the power plant to be dispatched, the output of each unit in the power plant to be dispatched is determined so that the generated dispatch plan meets the requirements of the lowest pollution emission and the lowest economic cost.

[0066] Preferably, the power plant to be dispatched provided in the embodiment of the present invention includes wind turbines. Therefore, when establishing a mathematical model of the power plant to be dispatched, in addition to modeling the thermal power plants, it is also necessary to consider the wind power output brought by wind power and the random fluctuations caused by the prediction error.

[0067] Due to the volatility and uncertainty of wind energy, the function used to reflect the distribution of wind speed can be the Weibull probability density function, and the mathematical model of wind power can be established as follows:

[0068]

[0069] When v <vin And v>v out ;

[0070]

[0071] When v wN <ν<υ out ;

[0072]

[0073] When in ≤ν≤v wN .

[0074] In the formula, f w (P w ) represents the Weibull probability distribution of wind power output, P w is the output power of the wind turbine, v is the actual wind speed, u wN is the rated wind speed of the fan, υ in and out are the cut-in wind speed and cut-out wind speed, c t and ε t are the scale parameter and shape parameter of the Weibull distribution at time t, P wN is the rated output power of the fan.

[0075] S120. According to the mathematical model of the power plant to be scheduled and in combination with the set algorithm, an initial scheduling plan set of the power plant to be scheduled is obtained.

[0076] The initial scheduling scheme set includes at least one initial scheduling scheme.

[0077] In this embodiment, after the mathematical model of the power plant to be scheduled is established, an algorithm can be used to output one or more initial scheduling plans as a set of initial scheduling plans, each of which sets the output of each unit in the power plant to be scheduled.

[0078] Preferably, the method for obtaining an initial set of scheduling schemes for the power plant to be scheduled based on the mathematical model of the power plant to be scheduled and in combination with the setting algorithm may be: using the target hybrid frog leaping algorithm as the setting algorithm, and determining the objective function and constraints of the target hybrid frog leaping algorithm based on the mathematical model of the power plant to be scheduled; randomly generating a first initialization population based on the target hybrid frog leaping algorithm; wherein the first initialization population includes at least one individual, and each individual corresponds to a scheduling scheme; optimizing and updating each individual in the first initialization population to obtain an optimized new population; and using the new population as the initial set of scheduling schemes for the power plant to be scheduled.

[0079] Among them, the objective function includes power generation cost function and pollution emission function.

[0080] Specifically, considering that the valve point effect of the steam turbine causes a single pulsation effect to overlap the unit energy consumption curve, the thermal power generation cost function can be established as follows:

[0081]

[0082] In the formula, F(P G ) is the overall energy consumption cost of N standard units in T time periods, a i , b i 、c i ,d i and e i are the fuel cost coefficients of the i-th thermal power unit, P i，t represents the actual output of the i-th thermal power unit in the t-th scheduling period, P i，min represents the minimum power of the i-th thermal power unit, P Gi represents the active power of the i-th thermal power unit, and the active output vector of the entire thermal power unit is P G .

[0083] P G =[P G1 , ..., P Gi , ..., P GN ]

[0084] After the wind turbine is connected to the grid, the total economic cost is the sum of the thermal power emission cost and the wind power cost. The final power generation cost function is as follows:

[0085] F=F(P G )+F(P w )

[0086] Among them, F(P G ) and F(P w ) are the thermal power generation cost and wind power generation cost respectively.

[0087] Regarding the pollution emission function, considering that there is a certain positive correlation between the emission of polluting gases and the active output of the unit, the pollution emission function can be determined as follows:

[0088]

[0089] In the formula, where: α i , β i , γ i , δ i , μ i is the coefficient of the pollutant gas emission characteristic equation of the i-th generator set.

[0090] Furthermore, the constraints of the algorithm include:

[0091] (1) Active output constraints of a single generator set in the system:

[0092] P Gimin ≤P Gi ≤P Gimax

[0093] Where P Gimax and P Gimin They respectively represent the maximum and minimum limits of the active output of the i-th generator set.

[0094] (2) System total active power constraint:

[0095]

[0096] Where P Gi , P D , P Loss They represent the active power of the i-th generator set, the active power of the load, and the total network loss of the system respectively.

[0097] (3) Unit climbing constraints:

[0098]

[0099] In the formula, ΔT represents the adjustment time. Under normal conditions, ΔT time should be reserved in similar scheduling periods to allow the unit power to be adjusted; P i，t and P i，t-1 Respectively represent the actual output of the i-th thermal power unit in the t and t-1 scheduling time periods, U Ri and D Ri are the up-climbing constraint and down-climbing constraint rates of the i-th thermal power unit respectively.

[0100] (4) Branch power transmission constraints:

[0101] S Li ≤S Limax， i=1,2,...,N L

[0102] In the formula, S Li and S Limax are the transmission power and transmission power upper limit of the i-th branch, N L is the number of branch lines.

[0103] (5) Spinning reserve constraints for wind power output:

[0104]

[0105] In the formula, is the uphill capacity that conventional wind turbine i can provide at time t, They are the positive spinning reserve demand caused by wind power and load forecast errors at time t respectively.

[0106]

[0107] In the formula, is the downhill capacity that conventional wind turbine i can provide at time t, They are the negative spinning reserve demand caused by wind power and load forecast errors at time t respectively.

[0108] Furthermore, the environmental economic dispatch of the power system is a strong-constrained multi-objective optimization problem, which includes multiple constraints such as power constraints, unit output constraints, and climbing constraints. When dealing with the impact of these constraints on the optimization results and dispatch, multiple factors need to be considered. If only feasible individuals are selected during the solution process, it is easy to fall into local optimization, and the population is also difficult to fully explore the target space. Therefore, in order to avoid this situation, it is necessary to consider how to make full use of individuals in the infeasible domain to obtain better optimization results. In fact, individuals in the infeasible domain often have better objective function values, and these individuals carry important "directional information". This information is very valuable in the solution process and can help the population better explore the target space and obtain a better solution. Therefore, it is necessary to find a way to make full use of this information to improve the quality of the optimization results. In this embodiment, the overall constraint violation degree is used to evaluate individuals. Specifically, the constraint violation degree is first normalized to eliminate the dimensional differences between different constraints. Then, the weighted average of all constraint violation degrees of each individual is calculated as the overall constraint violation degree of the individual. This value can reflect the constraint violation of the individual, and then be used to select and update the population. It should be noted that since different constraints have different meanings, their weights may also be different, so weighted processing is required when calculating the overall constraint violation. In the specific implementation, weights can be assigned according to the importance of the constraints and the degree of influence on the objective function, so as to obtain a more accurate overall constraint violation value. The calculation method is as follows:

[0109]

[0110] Where θ(x) is the violation degree of individual x, ω k =1 / T k，max is the weight coefficient, T k，max is the maximum constraint violation value corresponding to the kth constraint condition up to the current iteration number, S c is the total number of all equality constraints and inequality constraints, T k (x) is the kth constraint.

[0111] The weight coefficient is not fixed and will change as the number of iterations increases.

[0112] Preferably, the overall constraint violation threshold can be defined as θ. If the overall constraint violation does not exceed θ, the individual is judged as a feasible individual, otherwise it is an infeasible individual. In the actual optimization process, if the actual total number of iterations is G and the total number of individuals is N c , then in the first 40%G iterations, at most 10%N are selected each time c Individuals with a low overall constraint violation degree and a better objective function value enter the next generation; during the first 40%G to 70%G iterations, at most 5%N are selected in each generation. c The individuals with lower overall constraint violation and better function value enter the next generation, and the remaining 95%N are high-quality feasible individuals; and the last 30%G iterations ensure that all individuals entering the next generation are high-quality feasible individuals, so as to ensure the practical significance of the final solution set.

[0113] In this embodiment, the hybrid frog leaping algorithm can be used to generate the initial scheduling plan. Among them, the hybrid frog leaping optimization algorithm is an artificial intelligence algorithm proposed by Lansey KE in 2000 after observing and analyzing the activities of frogs, performing certain abstractions and mathematical modeling, and it can realize the global collaborative search function. After determining the objective function and constraints, the hybrid frog leaping algorithm can be used to randomly generate an initial population, and then optimize and update the individuals in the initial population, and use the new population composed of the optimized individuals as the initial scheduling plan set, wherein each individual in the population corresponds to a scheduling plan.

[0114] Optionally, the method for optimizing and updating each individual in the first initialized population to obtain the optimized new population may be: for each individual in the first initialized population, determine the crowding degree of each individual respectively; determine the worst individual in the first initialized population according to the crowding degree of each individual; randomly generate a new individual, and if the new individual is better than the worst individual, replace the worst individual with the new individual; return to execute the step of determining the worst individual in the first initialized population according to the crowding degree of each individual, until the set number of iterations is reached to obtain a new population.

[0115] The calculation method of congestion is as follows:

[0116]

[0117] In the formula, y cdi represents the crowding degree of individual i, n f represents the number of objective functions, and Represent the corresponding nth objective function values ​​of individuals i+1 and i-1 respectively. For an individual, if its crowding degree is too small, the area around the individual is extremely crowded, reflecting that the quality of the solution is poor and does not have sufficient reference value. If the value is too large, it means that the diversity of the solution is excellent and has a high reference value.

[0118] Furthermore, when updating the solution in the hybrid frog leaping algorithm, if both objectives of the new frog are better than the original frog, of course, it can be replaced decisively, but this situation is rare. In most cases, the two objective function values ​​are one large and one small, that is, solution A is indistinguishable from solution B, or the two are in a non-dominant relationship. If the solution is not replaced, the change is too small, which will lead to a lack of population diversity and easy to fall into local convergence. If both solutions are replaced, the change is too large, which is also not conducive to the convergence of the algorithm. Therefore, for this situation, a certain probability can be set to decide whether to replace the solution. Figure 2 : is a schematic diagram of an individual update process based on a hybrid frog leaping algorithm provided by an embodiment of the present invention. As shown in the figure, the process starts with setting relevant parameters, randomly generating a first initialization population, calculating the crowding degree of each individual in the first initialization population and sorting them, and updating the worst individual X w , and then randomly generate a new individual X new , to determine whether the new individual is better than the worst individual, that is, X new Dominate X? w If so, use the new individual X new Replace the worst individual X w Otherwise, generate a random number rand and check whether rand>0.5. If so, use the new individual X new Replace the worst individual X w , otherwise update the worst individual X w . Then judge X new Dominate X? w If so, use the new individual X new Replace the worst individual X w Otherwise, generate a random number rand and check whether rand>0.5. If so, use the new individual X new Replace the worst individual X w , otherwise a new individual X is randomly generated new and replace X w , until the population update is completed.

[0119] S130. Combined with the elite retention strategy, the initial scheduling plan set is screened, and the screening result is used as the target scheduling plan for the power plant to be scheduled.

[0120] In this embodiment, after the initial scheduling scheme is obtained, the elite retention strategy can be used to screen the initial scheduling scheme, so as to select a scheme with better performance as the target scheduling scheme.

[0121] Optionally, in combination with the elite retention strategy, the method for screening the initial scheduling plan set can be as follows: According to the target shuffled frog leaping algorithm, a second initial population is randomly generated; wherein, the second initial population contains at least one individual, and each individual corresponds to a scheduling plan; the initial scheduling plan set is used as the offspring population, and the offspring population and the second initial population are merged to obtain a new population; for each individual in the new population, the crowding degree of each individual is determined and sorted respectively, and a set number of individuals in the new population are retained in the order of crowding degree as the screening result.

[0122] Specifically, in combination with the target shuffled frog leaping algorithm, a second initial population can be randomly generated, denoted as P t and the initial scheduling plan set is used as the offspring population, denoted as Q t and then Q t is merged with P t to obtain a new population Y t . For each individual in the new population Y t , the crowding degree of each individual is determined and sorted respectively. If the population size of the new population is N2, N1 individuals can be screened out from it in the order of crowding degree as the screening result.

[0123] Furthermore, when screening according to the crowding degree of individuals, the new population Y t can be first non-dominated sorted to hierarchically process the individuals in the population, and then sorted according to the crowding degree for each layer respectively. Suppose the individuals in the population are divided into L layers, and the individuals in the same layer are at the same hierarchical level Rank. The hierarchical level of the individuals in the first layer is Rank1, and the hierarchical level of the Lth layer is denoted as RankL. After dividing the N2 individuals in the population into L layers through the non-dominated relationship, the individuals in the same hierarchical level need to be sorted in sequence, so it is necessary to analyze and calculate the crowding degree y cdi of all individuals in the same hierarchical level. The calculation method is as described in S120. According to the non-dominated sorting and crowding degree sorting, a new form of sorting method is obtained: for any two individuals i and j, if RankI < RankJ, then the solution corresponding to individual i can dominate individual j; if RankI = RankJ and y cdi > y cdj , then individual i dominates individual j. Figure 3This is a schematic diagram of a population screening process based on an elite retention strategy provided by an embodiment of the present invention. As shown in the figure, the process starts by setting algorithm parameters, randomly generating a second initialization population, then merging the offspring population with the second initialization population to obtain a new population, performing non-dominated sorting on the new population, and then calculating and sorting the crowding degree of each level of individuals obtained by the non-dominated sorting, and retaining the first N1 individuals of the new population as the parent population. Then merge the parent population with the offspring population, perform non-dominated sorting and crowding degree sorting, and iterate until the maximum number of iterations T is reached. max , output the final screening results.

[0124] The method for generating a power dispatching scheme provided by an embodiment of the present invention first obtains the power plant to be dispatched and determines the mathematical model of the power plant to be dispatched; then, based on the mathematical model of the power plant to be dispatched and in combination with a set algorithm, an initial dispatching scheme set for the power plant to be dispatched is obtained; wherein the initial dispatching scheme set includes at least one initial dispatching scheme; finally, in combination with an elite retention strategy, the initial dispatching scheme set is screened, and the screening result is used as the target dispatching scheme for the power plant to be dispatched. The method for generating a power dispatching scheme disclosed in the present invention obtains the initial dispatching scheme by using an algorithm, and then obtains the final target dispatching scheme by screening in combination with an elite retention strategy, so as to better find the optimal solution for complex problems, thereby obtaining a better power dispatching scheme.

[0125] Embodiment 2

[0126] Figure 4 A schematic diagram of the structure of a device for generating a power dispatching scheme provided in the second embodiment of the present invention is shown in FIG. Figure 4 As shown, the device includes: a mathematical model determination module 310, an initial scheduling solution set generation module 320 and a target scheduling solution determination module 330.

[0127] The mathematical model determination module 310 is used to obtain the power plant to be scheduled and determine the mathematical model of the power plant to be scheduled.

[0128] The initial scheduling scheme set generation module 320 is used to obtain an initial scheduling scheme set for the power plant to be scheduled based on the mathematical model of the power plant to be scheduled and in combination with a set algorithm.

[0129] The initial scheduling scheme set includes at least one initial scheduling scheme.

[0130] The target scheduling scheme determination module 330 is used to screen the initial scheduling scheme set in combination with the elite retention strategy, and use the screening result as the target scheduling scheme of the power plant to be scheduled.

[0131] Optionally, the power plant to be dispatched includes at least one wind turbine.

[0132] Optionally, the initial scheduling solution set generating module 320 is further used to:

[0133] The target hybrid frog leaping algorithm is used as the setting algorithm, and the objective function and constraint conditions of the target hybrid frog leaping algorithm are determined according to the mathematical model of the power plant to be scheduled; according to the target hybrid frog leaping algorithm, a first initialization population is randomly generated; wherein the first initialization population contains at least one individual, and each individual corresponds to a scheduling plan; each individual in the first initialization population is optimized and updated to obtain an optimized new population; and the new population is used as an initial scheduling plan set for the power plant to be scheduled.

[0134] Optionally, the objective function includes a power generation cost function and a pollution emission function.

[0135] Optionally, the initial scheduling solution set generating module 320 is further used to:

[0136] For each individual in the first initialized population, determine the crowding degree of each individual; determine the worst individual in the first initialized population according to the crowding degree of each individual; randomly generate a new individual, and if the new individual is better than the worst individual, replace the worst individual with the new individual; return to execute the step of determining the worst individual in the first initialized population according to the crowding degree of each individual until the set number of iterations is reached to obtain a new population.

[0137] Optionally, the target scheduling solution determination module 330 is further used to:

[0138] According to the target hybrid frog leaping algorithm, a second initialization population is randomly generated; wherein the second initialization population contains at least one individual, and each individual corresponds to a scheduling scheme; the initial scheduling scheme set is used as the offspring population, and the offspring population is merged with the second initialization population to obtain a new population; for each individual in the new population, the crowding degree of each individual is determined and sorted, and a set number of individuals in the new population are retained as the screening result in the order of crowding degree.

[0139] The device for generating a power dispatching scheme provided in the embodiment of the present invention can execute the method for generating a power dispatching scheme provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0140] Embodiment 3

[0141] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0142] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0143] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0144] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for generating a power dispatching scheme.

[0145] In some embodiments, the method for generating a power dispatching scheme may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of generating the power dispatching scheme described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for generating a power dispatching scheme in any other appropriate manner (e.g., by means of firmware).

[0146] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0148] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0151] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0152] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0153] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a power dispatching plan, characterized in that: include: Acquire a power plant to be scheduled and determine a mathematical model of the power plant to be scheduled; According to the mathematical model of the power plant to be scheduled, combined with the set algorithm, an initial scheduling scheme set of the power plant to be scheduled is obtained; wherein the initial scheduling scheme set includes at least one initial scheduling scheme; Combined with the elite retention strategy, the initial scheduling scheme set is screened, and the screening result is used as the target scheduling scheme of the power plant to be scheduled.

2. The method according to claim 1, characterized in that The power plant to be dispatched includes at least one wind turbine generator set.

3. The method according to claim 1, characterized in that According to the mathematical model of the power plant to be scheduled, combined with the set algorithm, an initial scheduling scheme set of the power plant to be scheduled is obtained, including: Using a target hybrid frog leaping algorithm as the setting algorithm, and determining an objective function and constraint conditions of the target hybrid frog leaping algorithm according to a mathematical model of the power plant to be scheduled; According to the target hybrid frog leaping algorithm, a first initialization population is randomly generated; wherein the first initialization population includes at least one individual, and each individual corresponds to a scheduling scheme; Optimizing and updating each individual in the first initialized population to obtain an optimized new population; The new population is used as an initial scheduling solution set for the power plant to be scheduled.

4. The method according to claim 3, characterized in that The objective function includes a power generation cost function and a pollution emission function.

5. The method according to claim 3, characterized in that: Optimizing and updating each individual in the first initialized population to obtain an optimized new population includes: For each individual in the first initialized population, determine the crowding degree of each individual respectively; Determine the worst individual in the first initialized population according to the crowding degree of each individual; Randomly generate a new individual, and if the new individual is better than the worst individual, the new individual is used to replace the worst individual; Return to the step of determining the worst individual in the first initialized population according to the crowding degree of each individual, until the set number of iterations is reached to obtain the new population.

6. The method according to claim 1, characterized in that Combined with the elite retention strategy, the initial scheduling solution set is screened, including: According to the target hybrid frog leaping algorithm, a second initialization population is randomly generated; wherein the second initialization population includes at least one individual, and each individual corresponds to a scheduling scheme; Using the initial scheduling solution set as a child population, and merging the child population with the second initialization population to obtain a new population; For each individual in the new population, the crowding degree of each individual is determined and sorted respectively, and a set number of individuals in the new population are retained as the screening result in the order of crowding degree.

7. A device for generating a power dispatching plan, characterized in that: include: A mathematical model determination module, used for acquiring a power plant to be scheduled and determining a mathematical model of the power plant to be scheduled; An initial scheduling scheme set generation module is used to obtain an initial scheduling scheme set of the power plant to be scheduled according to the mathematical model of the power plant to be scheduled and in combination with a set algorithm; wherein the initial scheduling scheme set includes at least one initial scheduling scheme; The target scheduling scheme determination module is used to screen the initial scheduling scheme set in combination with the elite retention strategy, and use the screening result as the target scheduling scheme of the power plant to be scheduled.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating a power dispatch plan according to any one of claims 1 to 6.

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 processor to implement the method for generating a power dispatching plan according to any one of claims 1 to 6 when executed.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for generating a power dispatching plan according to any one of claims 1 to 6 are implemented.

Images