CN112418715B - Method and device for generating wind power sequence scene set and storage medium - Google Patents
Method and device for generating wind power sequence scene set and storage medium Download PDFInfo
- Publication number
- CN112418715B CN112418715B CN202011436671.4A CN202011436671A CN112418715B CN 112418715 B CN112418715 B CN 112418715B CN 202011436671 A CN202011436671 A CN 202011436671A CN 112418715 B CN112418715 B CN 112418715B
- Authority
- CN
- China
- Prior art keywords
- wind power
- power sequence
- scene
- sequence scene
- scenes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method, a device and a storage medium for generating a wind power sequence scene set, which comprises the steps of firstly constructing a multi-objective optimization model for generating the required wind power sequence scene set, establishing a first objective function considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, establishing a second objective function considering the deviation of a second correlation coefficient of each time period of the wind power sequence scene set and a first correlation coefficient of each time period of an original wind power sequence scene, and an optimal group of N wind power sequence scenes is obtained by solving the model, so that the generated wind power sequence scene set can not only consider the comprehensiveness of the scenes, but also consider the correlation among the power of each time period in the wind power sequence scenes, and further ensure that the generated wind power sequence scenes are more accurate.
Description
Technical Field
The invention relates to the technical field of operation and planning of electric power systems, in particular to a method for generating a wind power sequence scene set.
Background
With the wind power plant scale of the access system getting bigger and bigger, the random characteristic of the wind power plant output cannot be ignored in the aspect of system analysis. The method can accurately reflect the original scene characteristics, has a less wind power sequence scene with future predictability, and has important reference significance for operation and planning of a power system containing large-scale wind power. At present, the generation method of the wind power scene in a single time interval has certain development and can be used for engineering practice; however, the wind power scenes of a plurality of periods, namely the generation of the wind power sequence scenes, are still in the starting stage. The method for generating the wind power sequence scene set mainly comprises a Monte Carlo method, a clustering method, a scene method optimization generation/reduction technology and a bidirectional optimization scene generation technology. The existing method has at least one of the following problems: (1) the wind power sequence obtained by reducing the historical sequence data is an already-generated historical scene, and the predictability of the future scene is lacked, namely the scene comprehensiveness is insufficient; (2) due to the calculation amount, the existing wind power sequence scene method generation method is suitable for the condition that an original scene set is small and is not directly suitable for the original scene set with large set elements; (3) the correlation between the power of each time segment in the wind power sequence scenario is not considered.
Disclosure of Invention
The embodiment of the invention aims to provide a method, a device and a storage medium for generating a wind power sequence scene set, so that the generated wind power sequence scene can not only consider the comprehensiveness of the scene, but also consider the correlation among powers of all time periods in the wind power sequence scene, and further ensure that the generated wind power sequence scene is more accurate.
The method for generating the wind power sequence scene set comprises the following steps:
establishing a multi-objective optimization model for generating a wind power sequence scene set, wherein the multi-objective optimization model comprises a first objective function, a second objective function and a multi-objective optimization function, the first objective function is established by considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, the second objective function is established by considering the deviation of a second correlation coefficient of each time period of the wind power sequence scene set and a first correlation coefficient of each time period of an original wind power sequence scene, and the multi-objective optimization function is established according to the first objective function and the second objective function, wherein the wind power sequence scene set comprises N wind power sequence scenes;
solving the multi-target optimization model by adopting a multi-target genetic algorithm to obtain a plurality of groups of candidate wind power sequence scene sets;
and obtaining an optimal group of wind power sequence scene sets from the multiple groups of candidate wind power sequence scene sets by adopting an analytic hierarchy process.
Preferably, the wind power sequence scene is constructed by the following steps:
collecting wind power data of historical periods, and constructing an original wind power sequence of a wind power plant;
processing the original wind power sequence by adopting a scene reduction technology to obtain an optimal representative scene of each time period;
and screening one scene from the optimal scenes of each time period, and connecting the screened scenes of each time period according to a time sequence to generate the wind power sequence scene.
Preferably, the establishing a first objective function considering the sum of distances of each wind power sequence scene in the wind power sequence scene set specifically includes:
establishing a first objective function according to the probability corresponding to each given wind power sequence scene and the wind power sequence scene set, specifically:
in the formula, beta i,t For the t time of the ith wind power sequence scenePower corresponding to the segment, beta j,t The power corresponding to the t time period of the jth wind power sequence scene, N is the number of wind power sequence scenes in the wind power sequence scene set, q is i And the probability corresponding to each given wind power sequence scene.
Preferably, the establishing a second objective function considering the deviation between the second correlation coefficient of each time interval of the wind power sequence scene set and the first correlation coefficient of each time interval of the original wind power sequence scene specifically includes:
acquiring a first correlation coefficient of each time interval of the original wind power sequence scene according to the following formula:
in the formula, p s The probability corresponding to the s-th original wind power sequence scene,
for the t th of the s th original wind power sequence scene 1 The power corresponding to the time period is,
for the t th of the s th original wind power sequence scene 2 The power corresponding to the time interval, S represents the number of original wind power sequence scenes;
acquiring a second correlation coefficient of each time interval of the wind power sequence scene set according to the following formula:
in the formula (I), the compound is shown in the specification,
for the t th wind power sequence scene of the ith 1 The power corresponding to each of the time periods,
for the t th wind power sequence scene of the ith 2 Power corresponding to each time period, q i For each given wind power sequence scenario corresponding probability, q i,j The probability corresponding to the jth time interval of the given ith wind power sequence scene;
then, the second objective function is specifically:
preferably, the establishing a multi-objective optimization function according to the first objective function and the second objective function specifically includes:
establishing and generating N wind power sequence scenes meeting the target according to the following functions:
F(x)＝min{f1,f2}。
preferably, after the step of screening one scene from the optimal scenes in each time period and connecting the screened one scene in each time period according to a time sequence to generate one wind power sequence scene, the method further includes:
screening one scene from the optimal scenes of each time period, and connecting the screened scenes of each time period according to a time sequence to obtain all wind power sequence scenes with the maximum possible number;
numbering all wind power sequence scenes according to the following steps:
the optimal scene for each time interval is expressed as 0,1, …, S T -1, numbering, the number of any wind power sequence scenario satisfies the following relation:
in the formula, l is a number corresponding to any wind power sequence, S j The number of the optimal scenes corresponding to the jth time interval; a is j And the number corresponding to the optimal scene selected for the jth time interval.
Preferably, the multi-objective optimization model is solved by using a multi-objective genetic algorithm to obtain multiple candidate wind power sequence scene sets, specifically:
randomly generating a plurality of groups of wind power sequence scene sets from all the wind power sequence scenes to form an initial population, wherein each group of wind power sequence scene set corresponds to an individual, and the individual is [ l ] 1 、l 2 、...、l N ]，l 1 、l 2 、...、l N Is the element of the individual and respectively represents the number corresponding to each wind power sequence scene in each group of the wind power sequence scene set, and has l 1 <l 2 <...<l N ；
Performing non-dominated sorting on the initial population, and obtaining a first generation progeny population through selection, crossing and variation of a genetic algorithm; when the numerical values of elements in new individuals generated by crossover or mutation are the same, randomly selecting a plurality of preset elements from the new individuals, and randomly changing the numerical values of the plurality of preset elements until the numerical value of each element in each individual is different;
combining the initial population and the first generation offspring population from the second generation, performing rapid non-dominant sorting, simultaneously performing crowding degree calculation on the individuals in each non-dominant layer, and selecting preset individuals according to the non-dominant relationship and the crowding degree of the individuals to form a new parent population;
and continuously iterating to generate new offspring populations through basic operation of a genetic algorithm until a preset maximum iteration number is reached, and obtaining multiple groups of candidate wind power sequence scene sets.
The embodiment of the present invention also provides a device for generating a wind power sequence scene set, which includes:
the model building module is used for building a multi-objective optimization model for generating a wind power sequence scene set, and comprises the steps of building a first objective function considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, building a second objective function considering the deviation of a second correlation coefficient of each time period of the wind power sequence scene set and a first correlation coefficient of each time period of an original wind power sequence scene, and building a multi-objective optimization function according to the first objective function and the second objective function, wherein the wind power sequence scene set comprises N wind power sequence scenes;
and the solving module is used for solving the multi-target optimization model by adopting a multi-target genetic algorithm to obtain a plurality of groups of candidate wind power sequence scene sets, and is also used for solving an optimal group of wind power sequence scene sets from the plurality of groups of candidate wind power sequence scene sets by adopting an analytic hierarchy process.
The embodiment of the present invention further provides a storage medium, where the storage medium includes a stored computer program, and when the computer program runs, a device where the storage medium is located is controlled to execute the method for generating the wind power sequence scene set according to the embodiment of the present invention.
Compared with the prior art, the method, the device, the terminal equipment and the storage medium for generating the wind power sequence scene set have the following remarkable effects:
the method for generating the wind power sequence scene set comprises the steps of establishing a first objective function considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, establishing a second objective function considering the deviation between a second correlation coefficient of each time interval of the wind power sequence scene set and a first correlation coefficient of each time interval of an original wind power sequence scene, establishing a multi-objective optimization function according to the first objective function and the second objective function, solving the multi-objective optimization model by adopting a multi-objective genetic algorithm to obtain a plurality of groups of candidate wind power sequence scene sets, and finally obtaining an optimal group of wind power sequence scene sets from the plurality of groups of candidate wind power sequence scene sets by adopting an analytic hierarchy process, the method for generating the wind power sequence scene set provided by the embodiment of the invention is suitable for an original scene set with larger set elements, and can accurately reflect the characteristics of the wind power sequence scene and predict the future foreseeable less wind power sequence scene by considering the correlation among the powers corresponding to all time periods in the wind power sequence scene during modeling, thereby providing technical support for the operation and planning of a power system comprising a large-scale wind power plant. The embodiment of the invention also correspondingly provides a generating device and a storage medium of the wind power sequence scene set.
Drawings
Fig. 1 is a schematic flow diagram of a method for generating a wind power sequence scene set according to an embodiment of the present invention;
fig. 2 is a hierarchical structure used by an analytic hierarchy process in the method for generating a wind power sequence scene set according to the embodiment of the present invention;
fig. 3 is a block diagram of a device for generating a wind power sequence scene set according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flow diagram of a method for generating a wind power sequence scene set according to an embodiment of the present invention.
The method for generating the wind power sequence scene set comprises the steps of S1-S3;
s1, constructing a multi-objective optimization model for generating a wind power sequence scene set, wherein the multi-objective optimization model comprises a first objective function considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, a second objective function considering the deviation between a second correlation coefficient of each time period of the wind power sequence scene set and a first correlation coefficient of each time period of an original wind power sequence scene, and a multi-objective optimization function according to the first objective function and the second objective function, wherein the wind power sequence scene set comprises N wind power sequence scenes.
As a specific implementation manner of the embodiment of the present invention, the wind power sequence scene is constructed by the following steps:
collecting wind power data of historical periods, and constructing an original wind power sequence of a wind power plant;
processing the original wind power sequence by adopting a scene reduction technology to obtain an optimal representative scene of each time period;
and screening one scene from the optimal scenes of each time period, and connecting the screened scenes of each time period according to a time sequence to generate the wind power sequence scene.
It can be understood that there are a plurality of optimal scenes in each time period, one scene is selected from the optimal representative scenes in each time period and is connected according to a time sequence, there are a plurality of wind power sequence scenes which can be formed and the number of which is very large, and if there are 10 optimal representative scenes in each time period, 10 can be generated in 24 time periods 24 And (4) a wind power sequence scene. Therefore, how to generate a small number of wind power sequence scenes from the huge number of wind power sequence scenes (i.e. N wind power sequence scenes to be generated by the present invention, the value of N can be set according to specific situation needs) needs to be studied to accurately reflect the original real scene of the original wind power sequence. In this way,according to the embodiment of the invention, a multi-objective optimization model for generating the wind power sequence scene set is established, an optimal group of wind power sequence scene sets (each group of wind power sequence scene sets comprises N wind power sequence scenes) is obtained by solving the model, and the characteristics of the wind power sequence scene are accurately reflected according to the finally generated wind power sequence scene set.
Preferably, the establishing a first objective function considering the sum of distances of each wind power sequence scene in the wind power sequence scene set specifically includes:
establishing a first objective function according to the probability corresponding to each given wind power sequence scene and the wind power sequence scene set, specifically:
in the formula, beta i,t Is the power, beta, corresponding to the t time interval of the ith wind power sequence scene j,t The power corresponding to the t time period of the jth wind power sequence scene, N is the number of wind power sequence scenes in the wind power sequence scene set, q is i And the probability corresponding to each given wind power sequence scene.
It can be understood that, in order to better embody the comprehensiveness of the wind power sequence scenes, the difference between the wind power sequence scenes in the generated wind power sequence scene set should be ensured to be as large as possible, that is, for the first objective function, the value of the first objective function should be made as large as possible.
Preferably, the establishing a second objective function considering a deviation between a second correlation coefficient of each time interval of the wind power sequence scene set and a first correlation coefficient of each time interval of the original wind power sequence scene specifically includes:
acquiring a first correlation coefficient of each time interval of the original wind power sequence scene according to the following formula:
in the formula p s Is the probability corresponding to the s-th original wind power sequence scene,
for the t th of the s th original wind power sequence scene 1 The power corresponding to the time period is,
for the t th of the s th original wind power sequence scene 2 The power corresponding to the time interval, S represents the number of original wind power sequence scenes;
acquiring a second correlation coefficient of each time interval of the wind power sequence scene set according to the following formula:
in the formula (I), the compound is shown in the specification,
for the t th wind power sequence scene of the ith 1 The power corresponding to each of the time periods,
for the t th wind power sequence scene of the ith 2 The power corresponding to each of the time periods,q i for each given wind power sequence scenario corresponding probability, q i,j The probability corresponding to the jth time interval of the given ith wind power sequence scene;
then, the second objective function is specifically:
preferably, the establishing a multi-objective optimization function according to the first objective function and the second objective function specifically includes:
establishing and generating N wind power sequence scenes meeting the target according to the following functions:
F(x)＝min{f1,f2}。
as a preferred implementation of the embodiment of the present invention, after the screening a scene from the optimal scenes in each time period, and connecting the screened scenes in each time period according to a time sequence to generate a wind power sequence scene, the method further includes:
screening one scene from the optimal scenes in each time period, and connecting the screened scenes in each time period according to a time sequence to obtain all wind power sequence scenes;
numbering all wind power sequence scenes according to the following steps:
the optimal scene for each time interval is expressed as 0,1, …, S T -1, numbering, the number of any wind power sequence scenario satisfies the following relation:
in the formula, l is a number corresponding to any wind power sequence, S j The number of the optimal scenes corresponding to the jth time interval; a is j And the number corresponding to the optimal scene selected for the jth time interval.
And S2, solving the multi-target optimization model by adopting a multi-target genetic algorithm to obtain a plurality of groups of candidate N wind power sequence scenes.
It can be understood that, by solving the above model by using a multi-objective genetic algorithm (NSGA-II), a Pareto optimal solution set, that is, the N wind power sequence scenes of the multiple candidate groups, can be obtained.
As a further improvement of the step S2, the multi-objective genetic algorithm is adopted to solve the multi-objective optimization model to obtain multiple candidate wind power sequence scene sets, which specifically include:
randomly generating a plurality of groups of wind power sequence scene sets from all the wind power sequence scenes to form an initial population, wherein each group of wind power sequence scene set corresponds to an individual, and the individual is [ l [ ] 1 、l 2 、...、l N ]，l 1 、l 2 、...、l N Is the element of the individual and respectively represents the number corresponding to each wind power sequence scene in each group of the wind power sequence scene set, and has l 1 <l 2 <...<l N ；
Performing non-dominated sorting on the initial population, and obtaining a first generation progeny population through selection, crossing and variation of a genetic algorithm; when the numerical values of elements in new individuals generated by crossover or variation are the same, randomly selecting a plurality of preset elements from the new individuals, and randomly changing the numerical values of the plurality of preset elements until the numerical value of each element in each individual is different;
combining the initial population and the first generation offspring population from the second generation, performing rapid non-dominant sorting, simultaneously performing crowding degree calculation on the individuals in each non-dominant layer, and selecting preset individuals according to the non-dominant relationship and the crowding degree of the individuals to form a new parent population;
and continuously iterating to generate new offspring populations through basic operation of a genetic algorithm until a preset maximum iteration number is reached, and obtaining multiple groups of candidate wind power sequence scene sets.
And S3, obtaining an optimal set of wind power sequence scene set from the multiple sets of candidate wind power sequence scene sets by adopting an analytic hierarchy process.
In the embodiment of the invention, an analytic hierarchy process is adopted to find the Pareto optimal solution from the Pareto optimal solution set, wherein the Pareto optimal solution is the optimal set of wind power sequence scene sets finally obtained in the embodiment of the invention.
Specifically, step S3 specifically includes the following steps:
(1) according to the principle of the hierarchical analysis method, referring to fig. 2, fig. 2 is a hierarchical structure used by the hierarchical analysis method in the method for generating the wind power sequence scene set according to the embodiment of the present invention, which specifically includes: the highest layer (total target layer) is the finally generated optimal set of wind power sequence scene sets, the middle layer (reference layer) is the first target function and the second target function, and the lowest layer (scheme layer) is the multiple sets of candidate wind power sequence scene sets Z obtained according to the step S2 i (i＝1,…,N′)。
(2) The adjacent upper and lower layers (the highest layer and the middle layer, the middle layer and the lowest layer) are respectively subjected to pairwise comparison analysis, and a 9-level comparison scale is adopted, as shown in table 1:
TABLE 1
(2-1) calculating to obtain an intermediate layer, namely a first objective function index f 1 And a second objective function index f 2 The judgment matrix a for the target layer (i.e. the set of finally generated optimal wind power sequence scene set) is as follows:
wherein, the element a in the matrix A ij Representative index f i Relative to the index f j The comparison result of (1).
(2-2) obtaining each group of candidate wind power sequence scene set Z i For the first objective function index f 1 Is determined by the matrix B 1 And each set of candidate wind powerSequence scene set Z i For the second target function index f 2 Is determined by the matrix B 2 ：
Wherein, the matrix B j Element (1) of
Is represented in index f j Candidate wind power sequence scene set Z k And candidate wind power sequence scene set Z l The comparison result of (1).
(3) According to the analytic hierarchy process, the matrix A and the matrix B are aligned j (j is 1,2) and the total level, if the consistency check is not passed, the matrix A and the matrix B need to be checked j (j-1, 2) re-modify until the consistency check is satisfied.
(4) When the consistency test is met, calculating the weight coefficient of each group of candidate wind power sequence scene sets to the finally generated optimal group of wind power sequence scene sets, selecting the group of candidate wind power sequence scene sets with the largest weight coefficient as the finally generated optimal group of wind power sequence scene sets, and acquiring the finally generated N wind power sequence scenes.
Referring to fig. 3, an embodiment of the present invention further provides a device for generating a wind power sequence scene set, including:
the model building module 1 is used for building a multi-objective optimization model for generating a wind power sequence scene set, and comprises the steps of building a first objective function considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, building a second objective function considering the deviation of a first correlation coefficient of each time period of the wind power sequence scene set and a second correlation coefficient of each time period of an original wind power sequence scene, and building a multi-objective optimization function according to the first objective function and the second objective function, wherein the wind power sequence scene set comprises N wind power sequence scenes;
and the solving module 2 is used for solving the multi-target optimization model by adopting a multi-target genetic algorithm to obtain a plurality of groups of candidate wind power sequence scene sets, and is also used for solving an optimal group of wind power sequence scene sets from the plurality of groups of candidate wind power sequence scene sets by adopting an analytic hierarchy process.
Another embodiment of the present invention provides a storage medium including a stored computer program, wherein the apparatus on which the storage medium is located is controlled to perform the steps S1 to S3 when the computer program runs.
The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, and software distribution medium, etc.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (7)
1. A generation method of a wind power sequence scene set is characterized by comprising the following steps:
establishing a multi-objective optimization model for generating a wind power sequence scene set, wherein the multi-objective optimization model comprises a first objective function for considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, a second objective function for considering the deviation of a second correlation coefficient of each time interval of the wind power sequence scene set and a first correlation coefficient of each time interval of an original wind power sequence scene, and a multi-objective optimization function according to the first objective function and the second objective function, wherein the wind power sequence scene set comprises N wind power sequence scenes;
solving the multi-target optimization model by adopting a multi-target genetic algorithm to obtain a plurality of groups of candidate wind power sequence scene sets;
obtaining an optimal group of wind power sequence scene sets from the multiple groups of candidate wind power sequence scene sets by adopting an analytic hierarchy process;
the establishing of the first objective function considering the sum of the distances of each wind power sequence scene in the wind power sequence scene set specifically includes:
establishing a first objective function according to the probability corresponding to each given wind power sequence scene and the wind power sequence scene set, specifically:
in the formula, beta i,t Is the power, beta, corresponding to the t time interval of the ith wind power sequence scene j,t The power corresponding to the t time period of the jth wind power sequence scene, N is the number of wind power sequence scenes in the wind power sequence scene set, q is i The probability corresponding to each given wind power sequence scene;
the establishing of the second objective function considering the deviation between the second correlation coefficient of each time interval of the wind power sequence scene set and the first correlation coefficient of each time interval of the original wind power sequence scene specifically includes:
acquiring a first correlation coefficient of each time interval of the original wind power sequence scene according to the following formula:
in the formula, p s The probability corresponding to the s-th original wind power sequence scene,
for the t th of the s th original wind power sequence scene 1 The power corresponding to the time period is,
for the t th of the s th original wind power sequence scene 2 The power corresponding to the time interval, S represents the number of original wind power sequence scenes;
acquiring a second correlation coefficient of each time interval of the wind power sequence scene set according to the following formula:
in the formula (I), the compound is shown in the specification,
for the t th wind power sequence scene of the ith 1 The power corresponding to each of the time periods,
for the t th wind power sequence scene of the ith 2 Power corresponding to each time period, q i For each given wind power sequence scenario corresponding probability, q i,j The probability corresponding to the jth time interval of the given ith wind power sequence scene;
then, the second objective function is specifically:
2. the method for generating the wind power sequence scene set according to claim 1, wherein the wind power sequence scene is constructed by the following steps:
collecting wind power data of historical periods, and constructing an original wind power sequence of a wind power plant;
processing the original wind power sequence by adopting a scene reduction technology to obtain an optimal representative scene of each time period;
and screening one scene from the optimal representative scenes of each time period, and connecting the screened scenes of each time period according to a time sequence to generate the wind power sequence scene.
3. The method for generating the wind power sequence scene set according to claim 1, wherein the establishing of the multi-objective optimization function according to the first objective function and the second objective function specifically comprises:
establishing and generating N wind power sequence scenes meeting the target according to the following functions:
F(x)＝min{f1,f2}。
4. the method for generating the wind power sequence scene set according to claim 2, wherein the method further comprises the steps of, after one scene is screened from the optimal representative scenes of each time period, and the screened one scene of each time period is connected according to a time sequence to generate one wind power sequence scene:
screening one scene from the optimal representative scenes of each time period, and connecting the screened scenes of each time period according to a time sequence to obtain all wind power sequence scenes;
numbering all wind power sequence scenes according to the following steps:
the optimal representative scene for each time interval is 0,1, …, S T -1, numbering, the number of any wind power sequence scenario satisfies the following relation:
in the formula, l is a number corresponding to any wind power sequence, S j The number of the optimal representative scenes corresponding to the jth time interval, a j And the number corresponding to the optimal representative scene selected for the j-th time interval.
5. The method for generating the wind power sequence scene set according to claim 4, wherein the multi-objective optimization model is solved by using a multi-objective genetic algorithm to obtain a plurality of candidate wind power sequence scene sets, specifically:
randomly generating a plurality of groups of wind power sequence scene sets from all the wind power sequence scenes to form an initial population, wherein each group of wind power sequence scene sets corresponds to an individual, and the individual is [ l [ ] 1 、l 2 、...、l N ]，l 1 、l 2 、...、l N Is an element of the individual and represents each groupThe number corresponding to each wind power sequence scene in the wind power sequence scene set is l 1 <l 2 <...<l N ；
Performing non-dominated sorting on the initial population, and obtaining a first generation progeny population through selection, crossing and variation of a genetic algorithm; when the numerical values of elements in new individuals generated by crossover or mutation are the same, randomly selecting a plurality of preset elements from the new individuals, and randomly changing the numerical values of the plurality of preset elements until the numerical value of each element in each individual is different;
combining the initial population and the first generation offspring population from the second generation, performing rapid non-domination sorting, simultaneously performing crowding degree calculation on the individuals in each non-domination layer, and selecting preset individuals according to the non-domination relationship and the crowding degree of the individuals to form a new parent population;
and continuously iterating to generate new offspring populations through basic operation of a genetic algorithm until a preset maximum iteration number is reached, and obtaining multiple groups of candidate wind power sequence scene sets.
6. A generation device of a wind power sequence scene set comprises the following steps:
the model building module is used for building a multi-objective optimization model for generating a wind power sequence scene set, and comprises the steps of building a first objective function considering the sum of distances of all wind power sequence scenes in the wind power sequence scene set, building a second objective function considering the deviation of a second correlation coefficient of each time period of the wind power sequence scene set and a first correlation coefficient of each time period of an original wind power sequence scene, and building a multi-objective optimization function according to the first objective function and the second objective function, wherein the wind power sequence scene set comprises N wind power sequence scenes;
the solving module is used for solving the multi-target optimization model by adopting a multi-target genetic algorithm to obtain a plurality of groups of candidate wind power sequence scene sets and is also used for solving an optimal group of wind power sequence scene sets from the plurality of groups of candidate wind power sequence scene sets by adopting an analytic hierarchy process;
the establishing of the first objective function considering the sum of the distances of each wind power sequence scene in the wind power sequence scene set specifically includes:
establishing a first objective function according to the probability corresponding to each given wind power sequence scene and the wind power sequence scene set, specifically:
in the formula, beta i,t Is the power, beta, corresponding to the t time interval of the ith wind power sequence scene j,t The power corresponding to the t time period of the jth wind power sequence scene, N is the number of wind power sequence scenes in the wind power sequence scene set, q is i The probability corresponding to each given wind power sequence scene;
the establishing of the second objective function considering the deviation between the second correlation coefficient of each time interval of the wind power sequence scene set and the first correlation coefficient of each time interval of the original wind power sequence scene specifically includes:
acquiring a first correlation coefficient of each time interval of the original wind power sequence scene according to the following formula:
in the formula, p s Is the probability corresponding to the s-th original wind power sequence scene,
is the s originalTth of wind power sequence scene 1 The power corresponding to the time period is,
for the t th of the s th original wind power sequence scene 2 The power corresponding to the time interval, S represents the number of original wind power sequence scenes;
acquiring a second correlation coefficient of each time interval of the wind power sequence scene set according to the following formula:
in the formula (I), the compound is shown in the specification,
for the t th wind power sequence scene of the ith 1 The power corresponding to each of the time periods,
for the t th wind power sequence scene of the ith 2 Power corresponding to each time period, q i For each given wind power sequence scenario corresponding probability, q i,j The probability corresponding to the jth time interval of the given ith wind power sequence scene;
then, the second objective function is specifically:
7. a storage medium, characterized in that the storage medium comprises a stored computer program, wherein when the computer program runs, the apparatus on which the storage medium is located is controlled to execute the method for generating a wind power sequence scene set according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011436671.4A CN112418715B (en) | 2020-12-11 | 2020-12-11 | Method and device for generating wind power sequence scene set and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011436671.4A CN112418715B (en) | 2020-12-11 | 2020-12-11 | Method and device for generating wind power sequence scene set and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112418715A CN112418715A (en) | 2021-02-26 |
| CN112418715B true CN112418715B (en) | 2022-09-16 |
Family
ID=74775033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011436671.4A Active CN112418715B (en) | 2020-12-11 | 2020-12-11 | Method and device for generating wind power sequence scene set and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418715B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401755A (en) * | 2020-03-19 | 2020-07-10 | 国电南瑞科技股份有限公司 | Multi-new-energy output scene generation method, device and system based on Markov chain |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040103013A1 (en) * | 2002-11-25 | 2004-05-27 | Joel Jameson | Optimal scenario forecasting, risk sharing, and risk trading |
| CN103219743B (en) * | 2013-03-25 | 2015-01-21 | 山东大学 | Pilot node selecting method based on wind electric power fluctuation probability characters |
| US20180352209A1 (en) * | 2017-06-02 | 2018-12-06 | Ostendo Technologies, Inc. | Methods and Systems for Light Field Compression Using Multiple Reference Depth Image-Based Rendering |
| CN107301472B (en) * | 2017-06-07 | 2020-06-26 | 天津大学 | Distributed photovoltaic planning method based on scene analysis method and voltage regulation strategy |
| CN109274134B (en) * | 2018-11-08 | 2020-06-16 | 东南大学 | Active power distribution network robust active and reactive power coordination optimization method based on time sequence scene analysis |
| KR20200112263A (en) * | 2019-03-21 | 2020-10-05 | 정호석 | System for integrated energy management based on demand managing and method teherefor |
| CN110288271B (en) * | 2019-07-11 | 2022-10-11 | 北京全来电科技有限公司 | Transformer district level charging load regulation and control strategy and method based on model predictive control |
| CN110912205B (en) * | 2019-11-26 | 2023-05-02 | 三峡大学 | Wind power system operation standby dynamic scheduling optimization method based on scene set |
| CN111639808B (en) * | 2020-05-29 | 2023-05-23 | 国网山东省电力公司经济技术研究院 | Multi-wind power plant output scene generation method and system considering space-time correlation |
-
2020
- 2020-12-11 CN CN202011436671.4A patent/CN112418715B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401755A (en) * | 2020-03-19 | 2020-07-10 | 国电南瑞科技股份有限公司 | Multi-new-energy output scene generation method, device and system based on Markov chain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112418715A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jia et al. | Multiobjective bilevel optimization for production-distribution planning problems using hybrid genetic algorithm | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| Ghadimi et al. | PSO based fuzzy stochastic long-term model for deployment of distributed energy resources in distribution systems with several objectives | |
| CN110262233B (en) | Optimization method for technological parameters of magnetic control film plating instrument | |
| CN113591299B (en) | Method and system for judging comprehensive performance of different types of micro-channel radiators | |
| CN107133695A (en) | A kind of wind power forecasting method and system | |
| Galvani et al. | Data clustering based probabilistic optimal power flow in power systems | |
| Peng et al. | An improved genetic algorithm based robust approach for stochastic dynamic facility layout problem | |
| CN111639838A (en) | Water quality monitoring point layout optimization method suitable for water supply pipe network | |
| Baesler et al. | Multi-response simulation optimization using stochastic genetic search within a goal programming framework | |
| CN114202174A (en) | Electricity price risk grade early warning method and device and storage medium | |
| CN112418715B (en) | Method and device for generating wind power sequence scene set and storage medium | |
| CN111651448B (en) | Low-voltage topology identification method based on noise reduction differential evolution | |
| CN113379116A (en) | Cluster and convolutional neural network-based line loss prediction method for transformer area | |
| Su et al. | Optimal placement and capacity sizing of energy storage systems via NSGA-II in active distribution network | |
| CN116502894A (en) | Photovoltaic transformer area power failure risk assessment method and device, electronic equipment and storage medium | |
| CN116432077A (en) | Intelligent station secondary system fault positioning method based on optimized BP neural network | |
| CN113919162B (en) | Voltage sag risk early warning method based on simulation and multi-source measured data fusion | |
| CN114066068A (en) | Short-term power load prediction method, device, equipment and storage medium | |
| CN114004008A (en) | Airplane assembly line resource configuration optimization method based on neural network and genetic algorithm | |
| Locsin et al. | Neural networks application for water distribution demand-driven decision support system | |
| CN112988404B (en) | Integrated circuit simulation coarse grain parallel method and device based on management process | |
| Indralaksono et al. | Hierarchical Clustering and Deep Learning for Short-Term Load Forecasting with Influenced Factors | |
| Hsieh | Employing data mining technique to achieve the parameter optimization based on manufacturing intelligence | |
| Ruihua et al. | Optimal reliability of composite power systems using genetic algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |