CN117767413A - Distributed photovoltaic power grid division method, device, equipment and storage medium - Google Patents
Distributed photovoltaic power grid division method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117767413A CN117767413A CN202311812973.0A CN202311812973A CN117767413A CN 117767413 A CN117767413 A CN 117767413A CN 202311812973 A CN202311812973 A CN 202311812973A CN 117767413 A CN117767413 A CN 117767413A
- Authority
- CN
- China
- Prior art keywords
- network topology
- topology structure
- distributed photovoltaic
- sample
- cluster
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 51
- 238000010586 diagram Methods 0.000 claims abstract description 47
- 239000011159 matrix material Substances 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000638 solvent extraction Methods 0.000 claims description 11
- 238000005192 partition Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 description 44
- 230000002068 genetic effect Effects 0.000 description 40
- 230000035772 mutation Effects 0.000 description 21
- 210000000349 chromosome Anatomy 0.000 description 19
- 230000008569 process Effects 0.000 description 15
- 238000004891 communication Methods 0.000 description 8
- 239000000243 solution Substances 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
- Y02E10/56—Power conversion systems, e.g. maximum power point trackers
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a distributed photovoltaic power grid dividing method, a device, equipment and a storage medium. The method comprises the following steps: acquiring a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: a connection state between every two nodes; determining a network topology structure diagram according to the connection state between every two nodes; inputting a network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by training an initial model through a training sample set, and the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample; and dividing the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid. By the technical scheme, the cluster optimization division of the distributed renewable energy sources can be realized.
Description
Technical Field
The embodiment of the invention relates to the technical field of large-scale power distribution network partitioning, in particular to a distributed photovoltaic power grid partitioning method, a device, equipment and a storage medium.
Background
In recent years, the photovoltaic power generation industry realizes rapid development, but along with large-scale access of distributed photovoltaic in a power distribution network, imbalance between high-permeability distributed photovoltaic power generation power and load demands can change the power flow distribution of the power distribution network, so that power flow is reversed, and the problem of voltage out-of-limit is serious.
In order to solve the problem of voltage digestion and ensure the reliability and stability of a power system, the method has great significance in developing cluster division optimization for a power distribution network containing high-permeability distributed photovoltaic. The dividing criterion method proposed at home and abroad is numerous, and the dividing algorithm of the current main stream mainly comprises: cluster analysis, community discovery algorithm, intelligent algorithm. Common clustering algorithms include hierarchical clustering, K-Means clustering, spectral clustering and the like; the community discovery algorithm comprises a louvain algorithm, a deep learning method of community detection and the like; the intelligent algorithm comprises a genetic algorithm, a particle swarm algorithm, a tabu search, simulated annealing, an ant colony algorithm and the like.
However, these algorithms proposed at present according to the purpose and requirements of grid management division have their drawbacks and disadvantages. Therefore, there is a need for a better method to achieve cluster optimization partitioning of distributed renewable energy sources.
Disclosure of Invention
The embodiment of the invention provides a distributed photovoltaic power grid dividing method, device, equipment and storage medium, which are used for obtaining a cluster dividing result according to the graph information of a power grid circuit topological structure through an improved genetic algorithm, so as to achieve the cluster optimization division of distributed renewable energy sources.
According to an aspect of the present invention, there is provided a distributed photovoltaic power grid dividing method, including:
acquiring a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: a connection state between every two nodes;
determining a network topology structure diagram according to the connection state between every two nodes;
inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by training an initial model through training a sample set, and the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample;
and dividing the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid.
According to another aspect of the present invention, there is provided a distributed photovoltaic grid dividing apparatus, the apparatus comprising:
the acquisition module is used for acquiring a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: a connection state between every two nodes;
the determining module is used for determining a network topology structure diagram according to the connection state between every two nodes;
the input module is used for inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by iteratively training an initial model through a training sample set, and the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample;
the dividing module is used for dividing the distributed photovoltaic power grid according to the cluster dividing result corresponding to the distributed photovoltaic power grid.
According to another aspect of the present invention, there is provided an electronic apparatus including:
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 distributed photovoltaic grid partitioning method of any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the distributed photovoltaic grid partitioning method according to any one of the embodiments of the present invention when executed.
The embodiment of the invention obtains a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: determining a network topology structure diagram according to the connection state between every two nodes, inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by iteratively training an initial model through a training sample set, and the training sample set comprises: the network topology structure diagram sample and the cluster division result sample corresponding to the network topology structure diagram sample divide the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid. According to the technical scheme, the cluster division result can be obtained according to the graph information of the power grid circuit topology structure through an improved genetic algorithm, so that the cluster optimization division of the distributed renewable energy sources is achieved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a distributed photovoltaic grid partitioning method in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an encoding process based on an improved genetic algorithm in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an initialization process based on an improved genetic algorithm in an embodiment of the present invention;
FIG. 4 is a schematic representation of a two-point crossover based on an improved genetic algorithm in an embodiment of the present invention;
FIG. 5 is a schematic representation of a node mutation based on an improved genetic algorithm in an embodiment of the present invention;
Fig. 6 is a schematic structural diagram of a distributed photovoltaic grid dividing device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device for implementing the distributed photovoltaic grid division method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.
Example 1
Fig. 1 is a flowchart of a distributed photovoltaic grid division method according to an embodiment of the present invention, where the embodiment is applicable to a distributed photovoltaic grid division situation, and the method may be performed by a distributed photovoltaic grid division device according to an embodiment of the present invention, where the device may be implemented in a software and/or hardware manner, as shown in fig. 1, and the method specifically includes the following steps:
s101, acquiring a data set of a distributed photovoltaic power grid.
In this embodiment, the distributed photovoltaic power grid may also be referred to as a power distribution network, where the distributed photovoltaic power grid includes at least two nodes, and the data set of the distributed photovoltaic power grid may include: the method comprises the steps of distribution network line parameters, sunrise data of each node, connection states between every two nodes, node types and distributed photovoltaic power related information. The power distribution network line parameters can comprise a network single line diagram, power cable impedance values and active and reactive output parameter values of all nodes, daily output data selection of all nodes of the power distribution network comprises net output power and meteorological data extracted once every 5 minutes, connection states between every two nodes can be divided into two nodes which are connected or not connected, and node types can comprise load nodes and distributed photovoltaic power supply nodes.
Specifically, a connection state between every two nodes in a data set of the distributed photovoltaic power grid is obtained.
S102, determining a network topology structure diagram according to the connection state between every two nodes.
In this embodiment, the network topology structure diagram may be an undirected graph formed by each node in the distributed photovoltaic power network and a connection state between every two nodes.
Specifically, according to the connection state of each node in the power distribution network as a data set, the data set is converted into an adjacent matrix form for representing an undirected unauthorized graph.
And S103, inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid.
In this embodiment, the target model may be a trained improved genetic algorithm model.
The cluster division result may be a plurality of clusters obtained by dividing the distributed photovoltaic power grid and output by the target model.
The target model is obtained by training an initial model through training a sample set, wherein the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample.
In this embodiment, the training sample set may be a network topology structure chart sample actually obtained for training an initial model and a cluster division result sample corresponding to the network topology structure chart sample, and the initial model may be an untrained and improved genetic algorithm model.
Specifically, inputting the network topology structure diagram into a trained improved genetic algorithm model to obtain a cluster division result corresponding to the distributed photovoltaic power grid.
S104, dividing the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid.
Specifically, the distributed photovoltaic power grid is divided according to a cluster division result corresponding to the distributed photovoltaic power grid output by the target model, a plurality of clusters are obtained, and the optimization division of the clusters of the distributed renewable energy sources is completed.
The embodiment of the invention obtains a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: determining a network topology structure diagram according to the connection state between every two nodes, inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by iteratively training an initial model through a training sample set, and the training sample set comprises: the network topology structure diagram sample and the cluster division result sample corresponding to the network topology structure diagram sample divide the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid. According to the technical scheme, the cluster division result can be obtained according to the graph information of the power grid circuit topology structure through an improved genetic algorithm, so that the cluster optimization division of the distributed renewable energy sources is achieved.
Optionally, iteratively training the initial model by training the sample set includes:
and establishing an initial model.
Inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample.
The prediction cluster dividing result may be a plurality of clusters obtained by dividing the network topology structure diagram sample output by the initial model.
And determining the fitness value according to a prediction cluster division result corresponding to the network topology structure diagram sample based on a preset fitness function.
In this embodiment, the preset fitness function may be a function preset by the user according to actual situations for evaluating a fitness value of the genetic algorithm. The fitness value may be a value obtained by calculating a prediction cluster division result according to a preset fitness function.
If the fitness value does not meet the preset target, training parameters of an initial model according to a prediction cluster division result corresponding to the network topology structure chart sample and an objective function formed by a cluster division result sample corresponding to the network topology structure chart sample.
In this embodiment, the preset target may be that the obtained fitness value is the largest, the objective function may be a loss function formed according to a prediction cluster division result corresponding to the network topology structure diagram sample and a cluster division result sample corresponding to the network topology structure diagram sample, and the parameter of the initial model may be the weight of the initial model.
Specifically, if the fitness value does not reach the preset target, the preset target may be, for example, a parameter of the initial model is trained according to a prediction cluster partition result corresponding to the network topology structure chart sample and an objective function formed by a cluster partition result sample corresponding to the network topology structure chart sample, where the fitness value is the maximum to a certain extent.
And returning to execute the operation of inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster dividing result corresponding to the network topology structure chart sample until the fitness value meets a preset target or the iteration number is greater than or equal to the preset number to obtain a target model.
The preset number of times may be a number of times threshold preset by the user according to an actual situation, which is not limited in this embodiment.
Specifically, training is continuously performed until the fitness value is maximum, or the iteration times reach the preset times, and determining the corresponding parameters when the fitness value is maximum as the weight of the target model to obtain the target model.
Optionally, the preset fitness function is composed of a first preset weight, a module degree index, a second preset weight and an active balance degree.
In this embodiment, the cluster division of the power grid is performed in an algorithm factor construction manner of a genetic algorithm designed based on the maximum modularity of a classical GN algorithm (Girvan-Newman algorithm).
As the fitness function in the improved genetic algorithm is an equation for solving multiple variables, the embodiment of the invention adds the fitness function variable parameters in the improved genetic algorithm, and adopts the self attribute of the node which relates to the modularity and the active balance degree.
The first preset weight may be a weight corresponding to a module degree index preset by a user according to an actual situation, and the second preset weight may be a weight corresponding to an active balance degree preset by the user according to an actual situation, for better research and calculation, the weights are generally normalized, that is, the sum of the first preset weight and the second preset weight is 1, but the specific numerical values of the first preset weight and the second preset weight are not limited in this embodiment.
In order to reveal a cluster structure of a distributed photovoltaic power grid network and represent a connection coupling strength relation among power grid nodes, the embodiment of the invention provides a module degree model, a maximized module degree increment is selected as an optimal fitness function parameter value, meanwhile, active balance is selected as the optimal fitness function parameter value, and a final preset fitness function is composed of a first preset weight, a module degree index, a second preset weight and the active balance.
Specifically, the preset fitness function may be expressed as:
wherein lambda is 1 Representing a first preset weight, sigma m As module index lambda 2 A second preset weight is indicated and is indicated,is the active balance degree.
Optionally, predicting the cluster partition result includes: at least one cluster, each cluster comprises at least one node, and attribute information carried by each node comprises: active power per node, reactive power per node, and voltage per node.
The method further comprises the steps of:
the target matrix is determined based on the active power of each node, the reactive power of each node, and the voltage of each node.
In this embodiment, the target matrix may be a sensitivity matrix of reactive power/voltage amplitude of each node, and may reflect a relationship between node voltage and node injection power.
In the actual operation process, since only the influence of reactive voltage sensitivity on the electrical distance is discussed, the influence of P increment is ignored, and the relation between power and voltage in the power system can be obtained through the derivation and the solution of the Newton Lapherson tide equation, the method comprises the following steps:
in a power transmission network, the reactance of a typical element is much larger than the resistance, and when P-Q decoupling is considered, the above equation can be simplified to obtain:
ΔQ＝L·ΔV；
Wherein Δp and Δq represent the increment of active power and reactive power injected into the node respectively; delta theta and delta V respectively represent node voltage phase angle and voltage amplitude increment; H. n, M, L are each a partition of a jacobian matrix; s for the present embodiment VQ And L is expressed, namely a sensitivity matrix of reactive power/voltage amplitude, and the relation between node voltage and node injection power is directly reflected.
And determining the electrical distance between every two nodes in the prediction cluster dividing result according to the target matrix.
In this embodiment, the electrical distance is used to measure how tightly the electrical coupling between each two nodes is.
Specifically, the calculation manner of predicting the electrical distance between every two nodes in the cluster division result may be expressed as follows:
wherein d ij Representing the electrical distance between node i and node j, represented by D ij Corresponding node variance value representation; d (D) ij The natural logarithm of the ratio of the jth row element to the ith row element in the jth column of the sensitivity matrix shows the voltage influence degree of the node j on the node i, D ij The smaller the electric connection between the node j and the node i is, the stronger the electric connection is, and the closer the corresponding electric distance is; s is S VQ,ij Representing S under reactive/voltage sensitivity matrix VQ Matrix ith row and jth column element values.
And determining a connecting edge weight value between every two nodes in the prediction cluster dividing result according to the electrical distance between every two nodes in the prediction cluster dividing result.
The connection edge weight value may be a weight value of an edge between two connected nodes.
Specifically, the calculation mode of the connection edge weight value between every two nodes in the prediction cluster partition result can be expressed as follows:
wherein B is ij To weight the edge connecting node i and node j, d ij Representing the electrical distance between node i and node j.
And determining a modularity index according to the weight value of the connecting edge between every two nodes in the prediction cluster division result.
Specifically, the modularity index determined according to the connection edge weight value between every two nodes in the prediction cluster division result may be expressed as:
wherein sigma m Is a modularity index; s is a node set in a prediction cluster dividing result; m is the sum of the edge weights of all edges in the prediction cluster division result; k (k) i Representing the sum of the weights of all edges connected to node i; Γ (i, j) is an optimization variable of the cluster partition problem.
Optionally, the attribute information carried by each node further includes: the payload power of each node.
The method further comprises the steps of:
the number of clusters in the prediction cluster division result, the number of nodes in each cluster and the payload power of each node are obtained.
And determining the active balance degree according to the number of clusters in the prediction cluster division result, the number of nodes in each cluster and the net load power of each node.
Specifically, the degree of active balanceThe calculation formula of (2) is expressed as follows:
wherein m represents the number of clusters; n (N) c Representing the number of clusters of cluster c; p (P) c (t) represents the total power of cluster c; p (P) i (t) represents the load power of the node i in the cluster at the time t; o (O) c Representing a set of nodes within cluster c; t is the time length of the time-varying scene.
In the actual operation process, the influence of the convergence of the iterative computation crossover and mutation probability values on the genetic algorithm is considered, and the embodiment designs a self-adaptive relationship restoration and adjustment.
The algorithm factor construction of the genetic algorithm is designed, and the content comprises code initialization, crossover, mutation and selection.
First, encoding and initializing. Reading the topology diagram data of each node connection circuit from the data set of the distributed photovoltaic power grid, converting the topology diagram data into chromosome coding values of 0-1 to form a symmetrical adjacency matrix A ij 。
FIG. 2 is a schematic diagram of an encoding process based on an improved genetic algorithm in an embodiment of the present invention. As shown in FIG. 2, to avoid the excessive scope of search when using genetic algorithm, the symmetric adjacency matrix is converted into an upper triangle representation, and then the binary decimal form d of the upper triangle is used i The N chromosomes are stored as 1 chromosome, so that the N chromosomes are stored, and the subsequent calculation is ensured. The initial adjacency matrix represents the network connection state before cluster division, and an unobtrusive adjacency matrix representation is applied:
In the encoding process, compared with the chromosome of the classical genetic algorithm, the designed genetic factors meet the following formula:
wherein A is ij The weight of the edge between the cluster network node i and the node j; d, d i Is the sum of the edge weights of the i-th row network edge.
FIG. 3 is a schematic diagram of an initialization process based on an improved genetic algorithm in an embodiment of the present invention. By the formulae i, j to U (1, num) node ) Conducting a random search, wherein num node Representing the number of network nodes. When the modified index value is obtained and the ith row and the jth column meet the requirement that the element value in the adjacent matrix is 1, random modification is carried out, and the random value of X=round (R) is 0 or 1, which respectively represents disconnection or connection, so that an initial genetic factor is provided as a cluster dividing structure. As shown in fig. 3, modifying 1 of row 2 and column 3 in the matrix to 0, i.e. modifying from connection to disconnection, corresponds to modifying node 3 from connection to disconnection with node 2.
Second, crossover, mutation and selection based on improved genetic algorithms. In order to find the individuals with high optimal adaptability and without losing the randomness and diversity of the selection process, a two-point crossing mode, a node mutation mode and an elite selection mode are adopted for the heuristic search algorithm.
The embodiment of the invention selects a two-point crossing mode to generate random numbers in a [0,1] interval, and when the random numbers are smaller than the crossing probability, two positions of two random chromosomes are crossed in an exchange way, and the mathematical expression is as follows:
P c_rand ＝U(0,1)；
P c_rand ≤P c ；
Wherein P is c_rand Representing the crossover probability of the random acquisition of the genetic factors; p (P) c The self-adaptive crossover probability changing along with the adaptability in the whole genetic process is represented; u (0, 1) represents a random number of 0-1.
Assuming that the ith row to the (i+1) th row of the A-th and B-th chromosomes of length n are selected to intersect, the formulas of the newly generated two chromosomes A 'and B' are expressed as follows:
A′＝a 1 a 2 ...a i-1 b i b i+1 a i+2 ...a n ；
B′＝b 1 b 2 ...b i-1 a i a i+1 b i+2 ...b n
wherein a=a 1 a 2 ...a n And b=b 1 b 2 ...b n Respectively representing the gene sequences of the two chromosomes.
The invention adopts a node mutation mode to randomly select the ith row and the jth column elements of the adjacent matrix from one chromosome for mutation. As with the crossover operation, when generating [0,1]The random number in the interval is smaller than the variation probability and satisfies the constraint formula P c_rand ≤P c In this case, a binary mutation operation is performed.
P m_rand ＝U(0,1)；
P m_rand ≤P m ；
Wherein: p (P) m_rand Representing the probability of variation randomly obtained by the genetic factor; p (P) m Indicating adaptive mutation probability as a function of fitness throughout the genetic process.
Suppose there are N total chromosomes Φ N The node mutation mode is adopted to make a certain genetic factor a m Randomly mutating to a' m Wherein for the adjacent matrix A corresponding to the genetic factors under the condition of meeting variation probability ij The expression is as follows:
Φ N ＝(a 1 ,a 2 ,...,a m ,...,a N )；
wherein a is mj (i) Representing the ith in the genetic element m The j-th conversion of the number corresponds to the quotient value, wherein a m(j-1) (i) X mod2 represents the binary value of the j-th row and the j-th column of the i-th row after the genetic factor m is converted into the adjacent matrix; n is a network node parameter; a is that ij Representation of genetic element a m A corresponding adjacency matrix.
Randomly selecting adjacency matrix A ij The i line and j column elements of the (a) are mutated, and the mutation condition of the genetic factors meets the following conditions: when the adjacent matrix element value corresponding to the factor of random mutation is 1, the random mutation is 0 or 1, and the random mutation represents the disconnection or connection state respectively; similarly, when the value of the corresponding adjacent matrix element is 0, if and only if the factor is connected with the original topological graph node, the random variation is considered, and the variation operation provides opportunities for new individuals and prevents the new individuals from falling into a local optimal solution, so that the evolution process is better simulated, and the optimal genetic factor is obtained.
The crossover and mutation design of the embodiments of the present invention are shown in fig. 4 and 5. Fig. 4 is a schematic diagram of two-point crossing based on an improved genetic algorithm in an embodiment of the present invention, and fig. 5 is a schematic diagram of node mutation based on an improved genetic algorithm in an embodiment of the present invention. As shown in fig. 4, in the N chromosome storage, two chromosomes are randomly selected to perform two-point crossing, for example, the a (6,2,0,0) and B (1, 0,2, 0) are subjected to two-point crossing, and specifically, the middle two bits of the two chromosomes can be respectively crossed to obtain (6,0,2,0) and (1,2,0,0). As shown in FIG. 5, 1 chromosome is randomly selected from N chromosome stores to perform node mutation, for example, the m (6,2,0,0) is subjected to node mutation when the probability mechanism is satisfied, and the (6,2,0,0) decimal system is converted into binary system to obtain And then node mutation is carried out, and specifically, 1 random change 0/1 of the 2 nd row and the 3 rd column can be saved.
In the actual operation process, the adjusting method considers that the chromosome modes are more similar as the iteration number is larger, so that the crossing rate and the mutation rate are properly increased as the iteration number is increased, and the local optimum is prevented from being trapped.
As an illustrative example of an embodiment of the present invention, the present invention refers to sunrise data of a certain day, and each photovoltaic power station acquires 288 data sets in total by data update every 5 min. Coding based on an original network adjacency matrix to generate an initial population, calculating individual fitness to store the optimal individual, judging whether iteration conditions are met, and if not, generating a next generation population based on selection, intersection and mutation strategies to replace an old population; if the result is satisfied, the best individual is output (the output best fitness value is 0.72951, the modularity is 0.742, the active balance is 0.4317), and the result of the decoding to obtain the cluster division is shown in table 1:
TABLE 1
The technical scheme of the embodiment of the invention mainly provides an improved genetic algorithm based on a classical Girvan-Newman algorithm aiming at the advantages of solving multiple discrete variables, optimizing multiple targets, influencing multiple environmental factors, reducing negative influence of inferior solutions and the like, and analyzes the construction method of algorithm factors of the improved genetic algorithm in detail, wherein the construction method comprises the establishment of a symmetrical adjacency matrix; converting the graphic information of the circuit topological graph into a chromosome coding form which can be processed by a genetic algorithm; generating chromosome changes, storage and optimization patterns, and the like. Through converting the image into digital codes, the thought of a multi-objective optimization problem is provided, and the cluster optimization division of the distributed renewable energy sources is achieved.
Example two
Fig. 6 is a schematic structural diagram of a distributed photovoltaic grid dividing device in an embodiment of the present invention. The embodiment may be applicable to the case of dividing a distributed photovoltaic power grid, and the device may be implemented in a software and/or hardware manner, and may be integrated in any device that provides a function of dividing a distributed photovoltaic power grid, as shown in fig. 6, where the device specifically includes: an acquisition module 201, a determination module 202, an input module 203 and a division module 204.
The acquiring module 201 is configured to acquire a data set of a distributed photovoltaic power grid, where the distributed photovoltaic power grid includes at least two nodes, and the data set includes: a connection state between every two nodes;
a determining module 202, configured to determine a network topology structure diagram according to a connection state between every two nodes;
the input module 203 is configured to input the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, where the target model is obtained by iteratively training an initial model through a training sample set, and the training sample set includes: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample;
And the dividing module 204 is configured to divide the distributed photovoltaic power grid according to a cluster division result corresponding to the distributed photovoltaic power grid.
Optionally, the input module 203 includes:
the building unit is used for building an initial model;
the input unit is used for inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample;
the first determining unit is used for determining a fitness value according to a prediction cluster dividing result corresponding to the network topology structure diagram sample based on a preset fitness function;
the training unit is used for training parameters of the initial model according to a prediction cluster division result corresponding to the network topology structure chart sample and an objective function formed by a cluster division result sample corresponding to the network topology structure chart sample if the fitness value does not meet a preset target;
and the execution unit is used for returning to the operation of inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample until the fitness value meets the preset target or the iteration number is greater than or equal to the preset number to obtain a target model.
Optionally, the preset fitness function is composed of a first preset weight, a module degree index, a second preset weight and an active balance degree.
Optionally, the predicting cluster partition result includes: at least one cluster, each cluster comprises at least one node, and attribute information carried by each node comprises: active power per node, reactive power per node, and voltage per node;
the apparatus further comprises:
a second determining unit, configured to determine a target matrix according to the active power of each node, the reactive power of each node, and the voltage of each node;
a third determining unit, configured to determine an electrical distance between every two nodes in the prediction cluster division result according to the target matrix;
a fourth determining unit, configured to determine a connection edge weight value between every two nodes in the prediction cluster division result according to an electrical distance between every two nodes in the prediction cluster division result;
and a fifth determining unit, configured to determine the modularity index according to a connection edge weight value between every two nodes in the prediction cluster division result.
Optionally, the attribute information carried by each node further includes: the payload power of each node;
The apparatus further comprises:
an obtaining unit, configured to obtain the number of clusters in the prediction cluster division result, the number of nodes in each cluster, and the payload power of each node;
and a sixth determining unit, configured to determine the active balance according to the number of clusters in the prediction cluster division result, the number of nodes in each cluster, and the payload power of each node.
The product can execute the distributed photovoltaic power grid dividing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the distributed photovoltaic power grid dividing method.
Example III
Fig. 7 shows a schematic diagram of an electronic device 30 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. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, 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. 7, the electronic device 30 includes at least one processor 31, and a memory such as a Read Only Memory (ROM) 32, a Random Access Memory (RAM) 33, etc., communicatively connected to the at least one processor 31, wherein the memory stores a computer program executable by the at least one processor, and the processor 31 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 32 or the computer program loaded from the storage unit 38 into the Random Access Memory (RAM) 33. In the RAM 33, various programs and data required for the operation of the electronic device 30 may also be stored. The processor 31, the ROM 32 and the RAM 33 are connected to each other via a bus 34. An input/output (I/O) interface 35 is also connected to bus 34.
Various components in electronic device 30 are connected to I/O interface 35, including: an input unit 36 such as a keyboard, a mouse, etc.; an output unit 37 such as various types of displays, speakers, and the like; a storage unit 38 such as a magnetic disk, an optical disk, or the like; and a communication unit 39 such as a network card, modem, wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 31 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 31 performs the various methods and processes described above, such as the distributed photovoltaic grid partitioning method:
acquiring a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: a connection state between every two nodes;
determining a network topology structure diagram according to the connection state between every two nodes;
inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by training an initial model through training a sample set, and the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample;
And dividing the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid.
In some embodiments, the distributed photovoltaic grid partitioning method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 30 via the ROM 32 and/or the communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the distributed photovoltaic grid dividing method described above may be performed. Alternatively, in other embodiments, the processor 31 may be configured to perform the distributed photovoltaic grid partitioning method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On 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, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out 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 implemented. The computer program may execute entirely on the 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. The 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 portable 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) through which a user can 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 may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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. The client and server are typically 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 hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The distributed photovoltaic power grid dividing method is characterized by comprising the following steps of:
acquiring a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: a connection state between every two nodes;
determining a network topology structure diagram according to the connection state between every two nodes;
inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by training an initial model through training a sample set, and the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample;
and dividing the distributed photovoltaic power grid according to the cluster division result corresponding to the distributed photovoltaic power grid.
2. The method of claim 1, wherein iteratively training the initial model by training the set of samples comprises:
establishing an initial model;
inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample;
Determining an fitness value according to a prediction cluster division result corresponding to the network topology structure diagram sample based on a preset fitness function;
if the fitness value does not meet the preset target, training parameters of the initial model according to a prediction cluster division result corresponding to the network topology structure chart sample and an objective function formed by a cluster division result sample corresponding to the network topology structure chart sample;
and returning to the operation of inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample until the fitness value meets the preset target or the iteration times are greater than or equal to the preset times to obtain a target model.
3. The method of claim 2, wherein the predetermined fitness function is comprised of a first predetermined weight, a modularity index, a second predetermined weight, and an active balance.
4. The method of claim 3, wherein predicting cluster partition results comprises: at least one cluster, each cluster comprises at least one node, and attribute information carried by each node comprises: active power per node, reactive power per node, and voltage per node;
Further comprises:
determining a target matrix according to the active power of each node, the reactive power of each node and the voltage of each node;
determining the electrical distance between every two nodes in the prediction cluster dividing result according to the target matrix;
determining a connection edge weight value between every two nodes in the prediction cluster division result according to the electrical distance between every two nodes in the prediction cluster division result;
and determining the modularity index according to the weight value of the connecting edge between every two nodes in the prediction cluster dividing result.
5. The method of claim 4, wherein the attribute information carried by each node further comprises: the payload power of each node;
further comprises:
acquiring the number of clusters in the prediction cluster division result, the number of nodes in each cluster and the payload power of each node;
and determining the active balance degree according to the number of clusters in the prediction cluster division result, the number of nodes in each cluster and the net load power of each node.
6. A distributed photovoltaic grid dividing device, comprising:
the acquisition module is used for acquiring a data set of a distributed photovoltaic power grid, wherein the distributed photovoltaic power grid comprises at least two nodes, and the data set comprises: a connection state between every two nodes;
The determining module is used for determining a network topology structure diagram according to the connection state between every two nodes;
the input module is used for inputting the network topology structure diagram into a target model to obtain a cluster division result corresponding to the distributed photovoltaic power grid, wherein the target model is obtained by iteratively training an initial model through a training sample set, and the training sample set comprises: the network topology structure chart sample and the cluster division result sample corresponding to the network topology structure chart sample;
the dividing module is used for dividing the distributed photovoltaic power grid according to the cluster dividing result corresponding to the distributed photovoltaic power grid.
7. The apparatus of claim 6, wherein the means for determining comprises:
the building unit is used for building an initial model;
the input unit is used for inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample;
the first determining unit is used for determining a fitness value according to a prediction cluster dividing result corresponding to the network topology structure diagram sample based on a preset fitness function;
the training unit is used for training parameters of the initial model according to a prediction cluster division result corresponding to the network topology structure chart sample and an objective function formed by a cluster division result sample corresponding to the network topology structure chart sample if the fitness value does not meet a preset target;
And the execution unit is used for returning to the operation of inputting the network topology structure chart sample in the training sample set into the initial model to obtain a prediction cluster division result corresponding to the network topology structure chart sample until the fitness value meets the preset target or the iteration number is greater than or equal to the preset number to obtain a target model.
8. The apparatus of claim 7, wherein the predetermined fitness function is comprised of a first predetermined weight, a module metric, a second predetermined weight, and an active balance.
9. An electronic device, the electronic device comprising:
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 distributed photovoltaic grid partitioning method of any one of claims 1-5.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the distributed photovoltaic grid partitioning method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311812973.0A CN117767413A (en) | 2023-12-26 | 2023-12-26 | Distributed photovoltaic power grid division method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311812973.0A CN117767413A (en) | 2023-12-26 | 2023-12-26 | Distributed photovoltaic power grid division method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117767413A true CN117767413A (en) | 2024-03-26 |
Family
ID=90321783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311812973.0A Pending CN117767413A (en) | 2023-12-26 | 2023-12-26 | Distributed photovoltaic power grid division method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117767413A (en) |
-
2023
- 2023-12-26 CN CN202311812973.0A patent/CN117767413A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106532778B (en) | Method for calculating maximum access capacity of distributed photovoltaic grid connection | |
| CN109714395A (en) | Cloud platform resource uses prediction technique and terminal device | |
| CN109840154B (en) | Task dependency-based computing migration method in mobile cloud environment | |
| CN103678346A (en) | Man-machine recognition method and system | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN114302418A (en) | Method and device for detecting network element equipment performance and computer readable medium | |
| WO2024056051A1 (en) | Non-intrusive flexible load aggregation characteristic identification and optimization method, apparatus, and device | |
| CN112887994A (en) | Wireless sensor network optimization method based on improved binary particle swarm and application | |
| CN115833101B (en) | Power scheduling method, device, electronic equipment and storage medium | |
| CN113408808A (en) | Training method, data generation method, device, electronic device and storage medium | |
| CN112036651A (en) | Electricity price prediction method based on quantum immune optimization BP neural network algorithm | |
| CN115222046A (en) | Neural network structure searching method and device, electronic equipment and storage medium | |
| Gang et al. | Dynamic economic emission dispatch with wind power based on improved multi‐objective brain storm optimisation algorithm | |
| CN116702598A (en) | Training method, device, equipment and storage medium for building achievement prediction model | |
| CN117973859A (en) | Risk prevention and control method, device, equipment and medium for main distribution network | |
| CN117332897A (en) | Artificial intelligent driven new energy small time scale power interpolation integrated prediction method | |
| CN107480724A (en) | A kind of determination method of cluster centre, determine system and a kind of clustering method | |
| CN111859807A (en) | Initial pressure optimizing method, device, equipment and storage medium for steam turbine | |
| CN116660756A (en) | Battery capacity attenuation curve generation method based on condition generation countermeasure network | |
| CN117767413A (en) | Distributed photovoltaic power grid division method, device, equipment and storage medium | |
| CN110288159A (en) | A kind of smart city construction Measurement Method | |
| CN115528684A (en) | Ultra-short-term load prediction method and device and electronic equipment | |
| CN115081551A (en) | RVM line loss model building method and system based on K-Means clustering and optimization | |
| Yang et al. | Self‐paced learning long short‐term memory based on intelligent optimization for robust wind power prediction | |
| CN109038609B (en) | Reactive power optimization method and system for power system |
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 |