CN115563507A - Generation method, device and equipment for renewable energy power generation scene - Google Patents
Generation method, device and equipment for renewable energy power generation scene Download PDFInfo
- Publication number
- CN115563507A CN115563507A CN202211358761.5A CN202211358761A CN115563507A CN 115563507 A CN115563507 A CN 115563507A CN 202211358761 A CN202211358761 A CN 202211358761A CN 115563507 A CN115563507 A CN 115563507A
- Authority
- CN
- China
- Prior art keywords
- scene
- power generation
- output sequence
- sequence sample
- generation
- 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.)
- Pending
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 144
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000005611 electricity Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 19
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 238000004140 cleaning Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 9
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013475 authorization Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and equipment for generating a renewable energy power generation scene, wherein the method comprises the following steps: acquiring a sample set of output sequences when renewable energy sources generate electricity; carrying out scene division on the output sequence sample set to obtain various initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample; training a scene generation model based on the multiple initial power generation scenes; and obtaining a target power generation scene based on the initial power generation scene and the trained scene generation model. By the method, the scene division is carried out on the output sequence sample set during the power generation of the renewable energy, the generation of the countermeasure network is combined, the scene generation model is trained, the construction of the typical scene generation model is completed, and the automatic generation of the typical scene of the renewable energy is realized.
Description
Technical Field
The embodiment of the invention relates to the technical field of power generation scene generation, in particular to a method, a device and equipment for generating a renewable energy power generation scene.
Background
With the advancement of industry and the rapid advancement of social modernization, the demand for electric power resources is continuously increasing, and the increasing global warming and the rapid consumption of fossil energy cause that the human society is facing huge pollution problems and energy shortage problems. These existing problems are driving the development of green, clean, efficient and sustainable power systems to meet the development needs of today's society.
Renewable energy power generation modes represented by wind power generation, solar power generation and the like begin to be connected to the grid on a large scale, the novel power generation modes have the characteristics of volatility, intermittency, randomness and the like, and the large-scale grid connection of the novel power generation modes brings great challenges to the safety and the stability of a power system. In order to research the influence of high-proportion renewable energy on a power system, the randomness and the volatility characteristics of renewable energy output need to be accurately described, and data simplification, data clustering and classical scene generation are carried out on renewable energy output data. The scene method and the interval method are two main methods for describing and analyzing the renewable energy output, wherein the scene analysis method has a more stable optimization effect. The higher the accuracy of a scene constructed by the scene analysis method is, the closer the solution of the corresponding random optimization problem is to the actual optimal value, so that the accurate construction of the renewable energy scene is an important research direction.
Disclosure of Invention
The embodiment of the invention provides a method, a device and equipment for generating a renewable energy power generation scene.
In a first aspect, an embodiment of the present invention provides a method for generating a renewable energy power generation scenario, where the method includes:
acquiring a sample set of output sequences when renewable energy sources generate electricity;
carrying out scene division on the output sequence sample set to obtain a plurality of initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample;
training a scene generation model based on the multiple initial power generation scenes;
and obtaining a target power generation scene based on the initial power generation scene and the trained scene generation model.
In a second aspect, an embodiment of the present invention further provides a device for generating a renewable energy power generation scenario, where the device includes:
the output sequence sample set acquisition module is used for acquiring an output sequence sample set during power generation of renewable energy;
the scene division module is used for carrying out scene division on the output sequence sample set to obtain a plurality of initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample;
the scene generation model training module is used for training a scene generation model based on the various initial power generation scenes;
and the target power generation scene acquisition module is used for acquiring a target power generation scene based on the initial power generation scene and the trained scene generation model.
In a third aspect, an embodiment of the present disclosure further provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the generation method of the renewable energy power generation scenario provided by the embodiment of the disclosure.
The invention discloses a method, a device and equipment for generating a renewable energy power generation scene, wherein the method comprises the following steps: acquiring a sample set of output sequences when renewable energy sources generate electricity; carrying out scene division on the output sequence sample set to obtain a plurality of initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample; training a scene generation model based on the multiple initial power generation scenes; and obtaining a target power generation scene based on the initial power generation scene and the trained scene generation model. By the method, the scene division is carried out on the output sequence sample set during the power generation of the renewable energy source, the generation countermeasure network is combined, the scene generation model is trained, the construction of the power generation scene generation model is completed, the automatic generation of the renewable energy source power generation scene is realized based on the scene generation model, and the generation efficiency of the power generation scene is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
Fig. 1 is a flowchart of a method for generating a renewable energy power generation scenario according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a first clustering process performed on an output sequence sample set after a cleaning process according to an embodiment of the present disclosure;
fig. 3 is a diagram of a generator network structure in a method for generating a renewable energy power generation scenario according to an embodiment of the present disclosure;
fig. 4 is a network structure of an arbiter in a method for generating a renewable energy power generation scenario according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a generating apparatus for a renewable energy power generation scenario provided in an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
It is understood that, before the technical solutions disclosed in the embodiments of the present disclosure are used, the user should be informed of the type, the use range, the use scene, etc. of the personal information related to the present disclosure in a proper manner according to the relevant laws and regulations and obtain the authorization of the user.
For example, in response to receiving a user's active request, prompt information is sent to the user to explicitly prompt the user that the requested operation to be performed would require acquisition and use of personal information to the user. Thus, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operations of the disclosed technical solution, according to the prompt information.
As an alternative but non-limiting implementation manner, in response to receiving an active request from the user, the manner of sending the prompt information to the user may be, for example, a pop-up window manner, and the prompt information may be presented in a text manner in the pop-up window. In addition, a selection control for providing personal information to the electronic device by the user's selection of "agreeing" or "disagreeing" can be carried in the pop-up window.
It is understood that the above notification and user authorization process is only illustrative and is not intended to limit the implementation of the present disclosure, and other ways of satisfying the relevant laws and regulations may be applied to the implementation of the present disclosure.
It will be appreciated that the data referred to in this disclosure, including but not limited to the data itself, the acquisition or use of the data, should comply with the requirements of the applicable laws and regulations and related regulations.
Example one
Fig. 1 is a flowchart of a method for generating a renewable energy power generation scenario provided in an embodiment of the present disclosure, where the embodiment of the present disclosure is applicable to a situation of automatic generation of a typical renewable energy scenario, and the method may be executed by a generation apparatus of a renewable energy power generation scenario, where the apparatus may be implemented in the form of software and/or hardware, and optionally implemented by an electronic device, where the electronic device may be a mobile terminal, a PC end, a server, or the like.
As shown in fig. 1, a method for generating a renewable energy power generation scenario provided in an embodiment of the present disclosure may specifically include the following steps:
and S110, acquiring an output sequence sample set during power generation of the renewable energy source.
In this embodiment, the renewable energy source may be green energy such as solar energy, wind energy, and water energy. The output sequence may be a sequence of a plurality of processed data, which may be understood as the generated power. In this embodiment, the output sequence acquires output data of various renewable energy sources during power generation, such as output data acquisition of photovoltaic power generation, wind power generation, hydroelectric power generation, and the like, through various intelligent acquisition devices and intelligent sensors on the end side. Namely, the output sequence sample data combination output sequence sample set collected under different scenes is obtained.
S120, carrying out scene division on the output sequence sample set to obtain various initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample.
It should be noted that the renewable energy data has a plurality of data sources, and each data source may have different power generation scenarios in different climates and environments, so that the output sequence sample set needs to be divided into a plurality of initial power generation scenarios.
In this embodiment, the manner of performing scene division on the output sequence sample set may be: firstly, preprocessing an output sequence sample set, and then sequentially clustering the preprocessed output sequence sample set twice. The preprocessing mode can be data cleaning on the output sequence sample set. The two Clustering processes may be a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm and a K-means (K-mean) Clustering algorithm, respectively. The density-based spatial clustering may also be referred to as a density clustering algorithm.
On the basis of the foregoing embodiment, the method for performing scene division on the output sequence sample set in the embodiment of the present disclosure may specifically include the following steps:
a1 A cleaning process is performed on the output sequence sample set.
In this embodiment, the output sequence sample set has a plurality of data sources, and various sensors are susceptible to various electromagnetic interference and natural factors during data acquisition, which results in phenomena such as power data loss and abnormal data generation, and therefore data cleaning is required. Specifically, the cleaning treatment method for the output sequence sample set may be: and removing abnormal data of which the data continuously missing in the output sequence sample set exceeds a first set threshold, and supplementing missing data for the abnormal data of which the missing data amount is less than a second set threshold by adopting a median determination method to obtain the cleaned output sequence sample set. Wherein the second set threshold is greater than the second set threshold.
b1 Performing first clustering processing on the cleaned output sequence sample set to obtain at least one output sequence sample cluster.
For the output sequence sample set after the cleaning process, for convenience of subsequent description, the set may be referred to as a D set. For sample set D = (X) 1 ,X 2 ,…,X m ) Wherein X is a sample of the output sequence, m is the total number of output sequences in the sample set of output sequences. The first clustering process may be understood as clustering by using a DBSCAN algorithm.
On the basis of the foregoing embodiment, in the embodiment of the present disclosure, the first clustering process may be performed on the output sequence sample set after the cleaning process, and obtaining at least one output sequence sample cluster may include the following steps:
b11 Determine a distance threshold and a quantity threshold based on the output sequence sample set after the cleaning process; the distance is the distance between two output sequence samples, and the number is the number of output sequence samples with the distance from the target output sequence sample within the distance threshold range.
The distance threshold may be understood as a domain radius value (eps) in the DBSCAN algorithm, and the quantity threshold may be understood as a domain density threshold (MinPts) in the DBSCAN algorithm. The distance threshold may be determined by: and calculating the distance between each output sequence in the output sequence sample set and all other output sequences, sequencing the distances according to the sequence from large to small to further obtain a distance curve, and setting the distance corresponding to the inflection point of the curve as a distance threshold value. The distance threshold is a critical threshold of the number of samples in the critical distance radius, and the distance threshold is calculated in the following way:
in the formula s i The number of output sequences in eps neighborhoods of the processing sequence i; n is a radical of hydrogen P The total number of contribution sequences in the set of contribution sequence samples.
b12 Based on the distance threshold and the quantity threshold, performing first clustering processing on the output sequence sample set after cleaning processing by adopting a density clustering algorithm to obtain at least one output sequence sample cluster.
Specifically, the process of performing the first clustering process by using the density clustering algorithm may be: based on the eps and MinPts, it is determined whether or not the point p in the sample set D that is not accessed is a core object point. If yes, storing the p points into the new cluster C. Newly building a set N, storing the points in eps of p into N, judging whether the points q which are not accessed in the set N are core object points, if so, storing the points with the distance from q being less than eps into N, and if not, judging whether q belongs to other clusters. And if not, adding the data into C until all data accesses in N are completed. And continuing to circularly judge whether the points which are not accessed and exist in the D are core object points or not, and the steps are the same until all the points in the D are accessed and the data which are not included in any cluster are marked as noise and output. And clustering the output sequence sample set by using a DBSCAN algorithm to obtain at least one output sequence sample cluster.
Here, the points p and q can be understood as a force sequence in the present embodiment.
And if not, the point is not the core object point, and the next point which is not accessed is continuously judged.
c1 Respectively performing second clustering treatment on at least one output sequence sample cluster to obtain a plurality of initial power generation scenes.
Wherein, a cluster of force sequence samples can be understood as a subset of a set of force sequence samples, including a plurality of force sequences. The second clustering process may be clustering using a K-mean algorithm. In this embodiment, for each output sequence sample cluster, a K-mean algorithm is used for clustering.
According to the scheme, the output sequence sample set is cleaned, and subjected to the first clustering and the second clustering, so that the scene of the output sequence sample set can be accurately divided.
On the basis of the above embodiment, the embodiment of the present disclosure may perform second clustering processing on at least one output sequence sample cluster, and specifically, obtaining multiple initial power generation scenarios may further include the following steps:
c11 Determine a cluster evaluation index.
Wherein, the cluster evaluation index can be a DB (Davies-Bouldin) index, and the DB index is defined as the following formula:
wherein c is the number of clusters; w i For data within class i to class centre C i Average distance of；W j For data within class i to class centre C j Average distance of (d); c ij Is the distance between class centers i and j. The smaller the value of the index is, the lower the inter-class similarity is, and the higher the class similarity is, the better the effect is.
c12 Performing second clustering treatment on at least one output sequence sample cluster by adopting a k-mean clustering algorithm based on the clustering evaluation index to obtain a plurality of initial power generation scenes.
Specifically, the second clustering process is performed on the output sequence sample cluster. Wherein. The process of clustering the output sequence sample clusters by using the k-mean clustering algorithm can refer to the principle of the existing k-mean clustering algorithm, and is not limited herein.
According to the scheme, the second clustering treatment is carried out on the output sequence sample cluster, so that the data classification is more accurate, and the clustering efficiency is improved.
On the basis of the foregoing embodiment, the embodiment of the present disclosure may specifically further include the following steps after obtaining at least one contribution sequence sample cluster:
a2 Respectively performing Kalman filtering processing on each output sequence sample in at least one output sequence sample cluster.
b2 Normalized for each output sequence sample after filtering.
c2 Correspondingly, the second clustering processing is respectively performed on at least one output sequence sample cluster, and the manner of obtaining multiple initial power generation scenes may be: and respectively carrying out second clustering treatment on the at least one output sequence sample cluster after the standardization treatment to obtain a plurality of initial power generation scenes.
Specifically, kalman filtering algorithm is used for filtering sample data of each output sequence in an output sequence sample cluster. And then performing second clustering treatment on the output sequence sample clusters, wherein the output sequence sample clusters are not influenced mutually. And performing initial clustering on the output sequence sample cluster, judging the clustering effect according to the clustering evaluation index, and obtaining the best clustered sample set through an iterative algorithm.
According to the technical scheme, the Kalman filtering algorithm is used for filtering the output sequence sample cluster, so that the data can be subjected to noise reduction, the complexity of the data is reduced, and the clustering efficiency is improved.
And S130, training the scene generation model based on various initial power generation scenes.
The scene generation model may be obtained based on a conditional generation countermeasure network (CGAN), which adds scene label (i.e., condition) inputs to both the generator and the arbiter inputs. The input of the generator is random noise and a scene label; the input of the discriminator is the real sample and scene label, or the sample and scene label is generated. The discriminator is used for judging whether the real sample is matched with the scene label or not, or judging whether the generated sample is matched with the scene label or not.
On the basis of the above embodiments, the training of the scene generation model based on multiple power generation scenes in the embodiments of the present disclosure may specifically include the following steps:
a3 Scene tags for a variety of power generation scenarios are obtained. Inputting the scene label and the first noise data into a generator, and outputting a generated sample; and inputting the generated sample and the scene label into a discriminator and outputting a first discrimination result.
b3 The output sequence samples and the corresponding scene labels are input into a discriminator to output a second discrimination result.
c3 Determining a loss function between the generated samples and the output sequence samples; and training the generator and the discriminator based on the first discrimination result, the second discrimination result and the loss function, and determining the trained generator as a scene generation model.
Specifically, the scene type of the power generation scene is used as a scene label, so that scene labels of various power generation scenes are obtained. Fig. 3 is a network structure diagram of a generator in a method for generating a renewable energy power generation scenario according to an embodiment of the present disclosure. As shown in fig. 3, the scene tag and the first noise data are input to the generator, and the generated sample is output. Fig. 4 is a network structure of an arbiter in a method for generating a renewable energy power generation scenario according to an embodiment of the present disclosure. As shown in fig. 4, the generated sample and the scene label are input to the discriminator, and the first discrimination result is output. And inputting the output sequence sample and the corresponding scene label into a discriminator and outputting a second discrimination result. Firstly, determining a first loss function based on a first discrimination result and a first real result, then determining a second loss function based on a second discrimination result and a second real result, then fusing the first loss function, the second loss function and the loss function to obtain a target loss function, finally training a generator and a discriminator based on the target loss function, and determining the trained generator as a scene generation model. The first loss function, the second loss function and the loss function may be fused for weighted summation.
Specifically, the way of training the generator and the arbiter based on the first and second discrimination results and the loss function may be: determining a first loss function based on the first discrimination result and the first real result, determining a second loss function based on the second discrimination result and the second real result, fusing the loss functions to obtain a target loss function, training the generator and the discriminator based on the target loss function, and determining the trained generator as a scene generation model.
The correlation and unknown relation of renewable energy processing is realized by constructing a conditional generation countermeasure network, and a widely used neural network model is constructed, so that the typical scene generation capability is improved.
On the basis of the above embodiment, the embodiment of the present disclosure may specifically further include the following steps after training the scene generation model based on multiple power generation scenes:
a4 Generate a verification power generation scenario based on the trained scenario generation model.
The verification power generation scene can be an output sequence, namely, the output sequence represents a power generation scene.
b4 Determining an evaluation index according to the verified power generation scene; wherein the evaluation index comprises an autocorrelation coefficient and/or a partial autocorrelation coefficient.
c4 Verifying the trained scene generation model based on the evaluation index.
d4 If the verification fails, continuing to train the scene generation model.
Specifically, an autocorrelation coefficient and/or a partial autocorrelation coefficient are/is selected to verify the correlation of the scene time sequence. When the autocorrelation coefficient and/or the partial autocorrelation coefficient of the power generation scene is higher than the set threshold value, the trained scene generation model can be considered to reach the preset result. Otherwise, the result of verifying the trained scene generating model based on the evaluation index does not reach the preset result, and the scene generating model continues to be trained.
In the technical scheme, uncertain factors are combined to a large extent through renewable energy scene generation, and the effectiveness of the generated scene is verified through calculating the correlation coefficient so as to ensure the scene generation effect and quality.
And S140, obtaining a target power generation scene based on the initial power generation scene and the trained scene generation model.
The target power generation scene can be an output sequence, namely, a power generation scene is represented by the output sequence. In this embodiment, the initial power generation scene obtained as described above is input into the trained scene generation model, so as to obtain a target power generation scene.
On the basis of the above embodiments, the generating of the target power generation scene based on the initial power generation scene and the trained scene generation model in the embodiments of the present disclosure specifically includes:
and inputting the scene label and the second noise data into the trained scene generation model, and outputting a target power generation scene.
Specifically, the second noise data is random noise data, the scene label and the random noise data are input into the trained scene generation model, and then different power generation scenes can be generated, wherein the generated power generation scenes are target power generation scenes.
The embodiment of the disclosure provides a method for generating a renewable energy power generation scene, which comprises the following steps: acquiring a sample set of output sequences when renewable energy sources generate electricity; carrying out scene division on the output sequence sample set to obtain various initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample; training a scene generation model based on various initial power generation scenes; and obtaining a target power generation scene based on the initial power generation scene and the trained scene generation model. By the method, the scene division is carried out on the output sequence sample set during the power generation of the renewable energy, the generation of the countermeasure network is combined, the scene generation model is trained, the construction of the typical scene generation model is completed, and the automatic generation of the typical scene of the renewable energy is realized.
Example two
Fig. 5 further provides a schematic structural diagram of a generating apparatus for a renewable energy power generation scenario, and as shown in fig. 5, the apparatus includes: the system comprises an output sequence sample set acquisition module 310, a scene division module 320, a scene generation model training module 330 and a target power generation scene acquisition module 340.
An output sequence sample set obtaining module 310, configured to obtain an output sequence sample set during power generation of a renewable energy source;
a scene division module 320, configured to perform scene division on the output sequence sample set to obtain multiple initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample;
a scene generation model training module 330, configured to train a scene generation model based on the multiple initial power generation scenes;
and a target power generation scene acquisition module 340, configured to acquire a target power generation scene based on the initial power generation scene and the trained scene generation model.
According to the technical scheme provided by the embodiment of the disclosure, the scene division is carried out on the output sequence sample set during the power generation of the renewable energy source, the generation of the countermeasure network is combined, the scene generation model is trained, the construction of the typical scene generation model is completed, and the automatic generation of the typical scene of the renewable energy source is realized.
Further, the scene partitioning module 320 may be configured to:
cleaning the output sequence sample set;
performing first clustering treatment on the cleaned output sequence sample set to obtain at least one output sequence sample cluster;
and respectively carrying out second clustering treatment on the at least one output sequence sample cluster to obtain a plurality of initial power generation scenes.
Further, the scene division module 320 may be further configured to:
determining a distance threshold and a quantity threshold based on the output sequence sample set after cleaning; the distance is a distance threshold value between two output sequence samples, and the number is the number of output sequence samples of which the distance from the target output sequence sample is within the distance threshold value range;
and performing first clustering processing on the output sequence sample set subjected to cleaning processing by adopting a density clustering algorithm based on the distance threshold and the quantity threshold to obtain at least one output sequence sample cluster.
Further, the scene division module 320 may be further configured to:
performing Kalman filtering processing on each output sequence sample in the at least one output sequence sample cluster respectively;
standardizing each output sequence sample after filtering;
correspondingly, performing second clustering treatment on the at least one output sequence sample cluster respectively to obtain a plurality of initial power generation scenes, including:
and respectively carrying out second clustering treatment on the at least one output sequence sample cluster after the standardization treatment to obtain a plurality of initial power generation scenes.
Further, the scene partitioning module 320 may be configured to:
determining a clustering evaluation index;
performing second clustering treatment on the at least one output sequence sample cluster by adopting a k-mean clustering algorithm based on the clustering evaluation index to obtain multiple initial power generation scenes
Further, the scene generation model training module 330 may also be configured to:
acquiring scene labels of the multiple power generation scenes;
inputting the scene label and first noise data into a generator, and outputting a generated sample;
inputting the generated sample and the scene label into a discriminator and outputting a first discrimination result;
inputting the output sequence sample and a scene label corresponding to the output sequence sample into the discriminator, and outputting a second discrimination result;
determining a loss function between the generated samples and the output sequence samples;
and training the generator and the discriminator based on the first discrimination result, the second discrimination result and the loss function, and determining the trained generator as a scene generation model.
Further, the scene generation model training module 330 may also be configured to:
generating a verification power generation scene based on the trained scene generation model;
determining an evaluation index according to the verification power generation scene; wherein the evaluation index comprises an autocorrelation coefficient and/or a partial autocorrelation coefficient;
verifying the trained scene generation model based on the evaluation index;
and if the verification fails, continuing to train the scene generation model.
Further, the target power generation scenario acquisition module 340 may be further configured to:
and inputting the scene label and the second noise data into a trained scene generation model, and outputting a target power generation scene.
The device can execute the methods provided by all the embodiments of the invention, and has corresponding functional modules and beneficial effects for executing the methods. For details not described in detail in this embodiment, reference may be made to the methods provided in all the foregoing embodiments of the present invention.
EXAMPLE III
FIG. 6 shows a schematic block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable 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 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
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, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of 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 suitable processor, controller, microcontroller, and so forth. The processor 11 performs the various methods and processes described above, such as the generation method of the renewable energy generation scenario.
In some embodiments, the generation method of the renewable energy power generation scenario may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto 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 the above described method of area division of a photovoltaic power plant may be performed. Alternatively, in other embodiments, the processor 11 may be configured by any other suitable means (e.g., by means of firmware) to perform the generation method of the renewable energy power generation scenario.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program 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, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can 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, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for generating a renewable energy power generation scene is characterized by comprising the following steps:
acquiring a sample set of output sequences when renewable energy sources generate electricity;
carrying out scene division on the output sequence sample set to obtain a plurality of initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample;
training a scene generation model based on the multiple initial power generation scenes;
and obtaining a target power generation scene based on the initial power generation scene and the trained scene generation model.
2. The method of claim 1, wherein scene partitioning the set of contribution sequence samples comprises:
cleaning the output sequence sample set;
performing first clustering processing on the cleaned output sequence sample set to obtain at least one output sequence sample cluster;
and respectively carrying out second clustering treatment on the at least one output sequence sample cluster to obtain a plurality of initial power generation scenes.
3. The method of claim 2, wherein the first clustering process is performed on the cleaned output sequence sample set to obtain at least one output sequence sample cluster, and comprises:
determining a distance threshold value and a quantity threshold value based on the output sequence sample set after cleaning; the distance is the distance between two output sequence samples, and the number is the number of output sequence samples of which the distance from the target output sequence sample is within the distance threshold range;
and performing first clustering processing on the cleaned output sequence sample set by adopting a density clustering algorithm based on the distance threshold and the quantity threshold to obtain at least one output sequence sample cluster.
4. The method of claim 2, further comprising, after obtaining at least one cluster of force sequence sample classes:
performing Kalman filtering processing on each output sequence sample in the at least one output sequence sample cluster respectively;
standardizing each output sequence sample after filtering;
correspondingly, performing second clustering treatment on the at least one output sequence sample cluster respectively to obtain a plurality of initial power generation scenes, including:
and respectively carrying out second clustering treatment on the at least one output sequence sample cluster after the standardization treatment to obtain various initial power generation scenes.
5. The method of claim 2, wherein the second clustering of the at least one output sequence sample cluster is performed to obtain a plurality of initial power generation scenarios, including:
determining a clustering evaluation index;
and performing second clustering treatment on the at least one output sequence sample cluster by adopting a k-mean clustering algorithm based on the clustering evaluation index to obtain various initial power generation scenes.
6. The method of claim 1, wherein training a scenario generation model based on the plurality of power generation scenarios comprises:
acquiring scene labels of the multiple power generation scenes;
inputting the scene label and first noise data into a generator, and outputting a generated sample;
inputting the generated sample and the scene label into a discriminator and outputting a first discrimination result;
inputting the output sequence sample and a scene label corresponding to the output sequence sample into the discriminator, and outputting a second discrimination result;
determining a loss function between the generated samples and the output sequence samples;
and training the generator and the discriminator based on the first discrimination result, the second discrimination result and the loss function, and determining the trained generator as a scene generation model.
7. The method of claim 1, after training a scenario generation model based on the plurality of power generation scenarios, further comprising:
generating a verification power generation scene based on the trained scene generation model;
determining an evaluation index according to the verification power generation scene; wherein the evaluation index comprises an autocorrelation coefficient and/or a partial autocorrelation coefficient;
verifying the trained scene generation model based on the evaluation indexes;
and if the verification fails, continuing to train the scene generation model.
8. The method of claim 6, wherein generating a target power generation scenario based on the initial power generation scenario and the trained scenario generative model comprises:
and inputting the scene label and the second noise data into a trained scene generation model, and outputting a target power generation scene.
9. A generation device of a renewable energy power generation scene is characterized by comprising:
the output sequence sample set acquisition module is used for acquiring an output sequence sample set during power generation of the renewable energy source;
the scene division module is used for carrying out scene division on the output sequence sample set to obtain a plurality of initial power generation scenes; the initial power generation scene is an output sequence sample subset and comprises at least one output sequence sample;
the scene generation model training module is used for training a scene generation model based on the various initial power generation scenes;
and the target power generation scene acquisition module is used for acquiring a target power generation scene based on the initial power generation scene and the trained scene generation model.
10. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of generating a renewable energy power generation scenario of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211358761.5A CN115563507A (en) | 2022-11-01 | 2022-11-01 | Generation method, device and equipment for renewable energy power generation scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211358761.5A CN115563507A (en) | 2022-11-01 | 2022-11-01 | Generation method, device and equipment for renewable energy power generation scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115563507A true CN115563507A (en) | 2023-01-03 |
Family
ID=84767986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211358761.5A Pending CN115563507A (en) | 2022-11-01 | 2022-11-01 | Generation method, device and equipment for renewable energy power generation scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563507A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116227751A (en) * | 2023-05-09 | 2023-06-06 | 国网吉林省电力有限公司经济技术研究院 | Optimal configuration method and device for power distribution network |
-
2022
- 2022-11-01 CN CN202211358761.5A patent/CN115563507A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116227751A (en) * | 2023-05-09 | 2023-06-06 | 国网吉林省电力有限公司经济技术研究院 | Optimal configuration method and device for power distribution network |
| CN116227751B (en) * | 2023-05-09 | 2023-07-07 | 国网吉林省电力有限公司经济技术研究院 | Optimal configuration method and device for power distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117078048B (en) | Digital twinning-based intelligent city resource management method and system | |
| CN112560985A (en) | Neural network searching method and device and electronic equipment | |
| CN109449923B (en) | Quantitative analysis method for operation flexibility of active power distribution system and related product | |
| CN113051911A (en) | Method, apparatus, device, medium, and program product for extracting sensitive word | |
| CN112580666A (en) | Image feature extraction method, training method, device, electronic equipment and medium | |
| CN113408808A (en) | Training method, data generation method, device, electronic device and storage medium | |
| CN115563507A (en) | Generation method, device and equipment for renewable energy power generation scene | |
| CN115294397A (en) | Classification task post-processing method, device, equipment and storage medium | |
| CN114692778A (en) | Multi-modal sample set generation method, training method and device for intelligent inspection | |
| CN114581732A (en) | Image processing and model training method, device, equipment and storage medium | |
| CN117235608B (en) | Risk detection method, risk detection device, electronic equipment and storage medium | |
| CN113554280A (en) | Training method, device, equipment and storage medium for power grid system scheduling model | |
| Xu et al. | An improved SMURF scheme for cleaning RFID data | |
| CN113052509B (en) | Model evaluation method, model evaluation device, electronic apparatus, and storage medium | |
| CN113326885A (en) | Method and device for training classification model and data classification | |
| CN113886543A (en) | Method, apparatus, medium, and program product for generating an intent recognition model | |
| CN114120410A (en) | Method, apparatus, device, medium and product for generating label information | |
| CN113947195A (en) | Model determination method and device, electronic equipment and memory | |
| CN115964478A (en) | Network attack detection method, model training method and device, equipment and medium | |
| CN114938385B (en) | Electric power physical network security situation awareness method, device, equipment and medium | |
| CN118822013A (en) | Method, device, equipment and medium for predicting generated power | |
| CN116128296A (en) | Risk prediction method, risk prediction device, electronic equipment and storage medium | |
| CN116111562A (en) | Method, device, equipment and storage medium for determining reliability of power distribution network | |
| CN117609723A (en) | Object identification method and device, electronic equipment and storage medium | |
| CN117667488A (en) | Abnormal positioning method, device, equipment and medium for artificial intelligent computing power cluster |
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 |