CN114169118B - Power distribution network topological structure identification method considering distributed power output correlation - Google Patents
Power distribution network topological structure identification method considering distributed power output correlation Download PDFInfo
- Publication number
- CN114169118B CN114169118B CN202111551789.6A CN202111551789A CN114169118B CN 114169118 B CN114169118 B CN 114169118B CN 202111551789 A CN202111551789 A CN 202111551789A CN 114169118 B CN114169118 B CN 114169118B
- Authority
- CN
- China
- Prior art keywords
- node
- voltage amplitude
- distribution network
- power distribution
- maximum
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 24
- 238000002347 injection Methods 0.000 claims abstract description 20
- 239000007924 injection Substances 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000005259 measurement Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
In an off-line stage, the preprocessed power grid data is used as a training set to train a neural network, in an on-line stage, a synthesized node voltage amplitude sample is obtained through the trained neural network input by a test set, and then the power distribution network topology is identified by adopting a maximum spanning tree algorithm based on a maximum information coefficient to obtain all node pairs of the power distribution network, wherein each node pair represents one side in the power distribution network topology and is used as a power distribution network topology identification result. The invention adopts a neural network to establish the relation between node voltage amplitude and node injection power, and proposes a maximum spanning tree algorithm based on a maximum information coefficient to identify the topological structure of the power distribution network.
Description
Technical Field
The invention relates to a technology for analyzing the running state of a power distribution network, in particular to a power distribution network topological structure identification method considering the output correlation of a distributed power supply.
Background
The power system topology abstracts the grid into a graph containing nodes and edges. The nodes of the graph represent nodes in a power grid and are connected with equipment such as a generator, a distributed power supply, a load and the like; the edges of the figure represent lines in the grid. The topology structure of the power system describes the connection relation among all nodes in the power grid, and is an important basis for analysis and application of power system optimization operation, fault positioning, power failure management and the like. In general, the power system operators can accurately solve the topology structure of the power transmission network, and only need to identify the errors of the topology structure according to the more complete measurement information. However, because of numerous nodes and branches of the power distribution network, measurement information is incomplete and a topology structure is frequently changed, and particularly, the topology structure of the power distribution network is difficult to accurately obtain under the background that a distributed power supply is accessed into the power distribution network in a large scale.
With the wide deployment of advanced metrology systems (ADVANCED METERING Infrastructure, AMI) and data acquisition and monitoring control systems (Supervisory Control And DataAcquisition, SCADA), node voltage amplitude and injection power measurement information can be obtained, which is of great value for topology identification. The existing power distribution network topological structure method depends on certain assumption conditions, such as known power distribution network line parameters, independent node injection power, normal distribution compliance of node voltage and the like.
Disclosure of Invention
Aiming at the defects of the prior method, the invention provides a power distribution network topological structure identification method considering the output correlation of a distributed power supply, a neural network is adopted to establish the relation between the node voltage amplitude and the node injection power, and a maximum spanning tree algorithm based on the maximum information coefficient is provided for carrying out the power distribution network topological structure identification.
The invention is realized by the following technical scheme:
The invention relates to a power distribution network topological structure identification method considering the output correlation of a distributed power supply, which is characterized in that preprocessed power grid data is used as a training set to train a neural network in an off-line stage, a synthesized node voltage amplitude sample is obtained by inputting the trained neural network through a test set in an on-line stage, and then the power distribution network topological structure identification is carried out by adopting a maximum spanning tree algorithm based on a maximum information coefficient to obtain all node pairs of the power distribution network, wherein each node pair represents one edge in the power distribution network topological structure and is used as a power distribution network topological structure identification result.
The power grid data is node injection power and node voltage amplitude measurement data of all nodes of the power grid.
The pretreatment is as follows: after the injection power measurement P i of the node i is converted into a random variable P n,i conforming to standard normal distribution, calculating a covariance matrix sigma of P n={pn,1,pn,2,…,pn,N, and then obtaining a lower triangular matrix L by adopting Cholesky decomposition to obtain an input sample P t=L-1Pn T of a neural network training set, wherein: i=1, 2, …, N.
The training set refers to a set of training set input samples P t and training set output samples, namely node voltage amplitude measurement U t={u1,u2,…,uN.
The test set is obtained by the following steps:
1) Calculating standard deviation vector Wherein: /(I)The ith row and the kth column of matrix L -1.
2) A random variable p c,i with a mean value of 0 and a standard deviation of σ i, which obeys an independent normal distribution, is generated.
3) A test set input sample P s=L-1Pc T is obtained, where P c={pc,1,pc,2,…,pc,N.
The neural network includes: preprocessing module, input layer, hidden layer and output layer, wherein: the preprocessing module converts the node voltage amplitude corresponding to the node injection power with correlation into the node voltage amplitude corresponding to the independent node injection power.
The number of neurons of the input layer is node number minus 1, the number of hidden layers is 2, the number of neurons is 1000, and the number of neurons of the output layer is node number minus 1.
The maximum spanning tree algorithm based on the maximum information coefficient specifically comprises the following steps:
i) A graph T is built containing N nodes.
Ii) calculating the maximum information coefficient of all nodes to the voltage amplitude.
Iii) All node pairs are arranged in the order of the maximum information coefficient of the voltage amplitude from large to small, and the ordered node pairs are represented by e k, k=1, 2, … and N (N-1)/2.
Iv) adding e 1 and e 2 to map T.
V) set k=3.
Vi) when the number of edges in the graph T is less than N-1, performing steps vii) to ix), otherwise going to step x):
vii) when e k is added to figure T, no ring is formed, then e k is added to figure T.
viii)k=k+1。
Ix) when k > N (N-1)/2, go to step x), otherwise go to step vi).
X) the obtained graph T is the topology identification result.
The invention relates to a system for realizing the method, which comprises the following steps: the system comprises a data reading module, a preprocessing module, a synthesized node voltage amplitude generating module, a maximum spanning tree algorithm module and a result output module which are sequentially connected, wherein: the data reading module reads the node injection power and node voltage amplitude measurement data of the power distribution network; the preprocessing module generates a neural network training set and a test set sample according to the node injection power and the node voltage amplitude measurement data; the synthesized node voltage amplitude generating module obtains synthesized node voltage amplitude by adopting a neural network; the maximum spanning tree algorithm module obtains a maximum spanning tree according to the maximum information coefficient among the synthesized node voltage amplitudes; the result output module outputs the maximum spanning tree as a topology identification result.
Technical effects
The invention utilizes normal distribution property, transforms the neural network input set of different distributions into the input set obeying the same distribution through cumulative distribution function transformation, ensures that the coverage of the training sample input set comprises the test sample input set, improves the training precision of the neural network, and simultaneously, accurately calculates the relevance of node voltage amplitude measurement by adopting the maximum information coefficient through the maximum spanning tree algorithm based on the maximum information coefficient, and improves the precision of the topological structure identification algorithm. Compared with the prior art, the topology structure identification method effectively considers the influence of the output correlation of the distributed power supply, and obtains an accurate topology structure identification result of the power distribution network on the premise that the known power distribution network line parameters are not needed, the node injection power is not needed to be independent and the node voltage amplitude probability distribution is not needed to be assumed.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a wiring diagram of an embodiment IEEE 69 node system;
FIG. 3 is a schematic diagram of the effect of the embodiment.
Detailed Description
As shown in fig. 2, in this embodiment, an IEEE 69 node standard system is taken as an example, the node injection power measurement data disclosed by the actual power distribution network is adopted, the sampling scale is set to be 8000, the neural network adopted in this embodiment is a fully-connected neural network, the number of neurons in the hidden layer is 1000, an Adam optimizer and a root mean square loss function are adopted, and the learning rate is set to be 5e-4.
The embodiment specifically comprises the following steps:
Step 1) obtaining grid data, and obtaining a node injection power measurement sample p i (i=1, 2, …, 69) and node voltage amplitude measurement samples u i(i=1,2,…,69).pi and u i which are vectors with dimensions of 8000.
Step 2) converting p i into a random variable p n,i conforming to a standard normal distribution, specifically comprising:
i) The cumulative distribution function value c k (k=1, 2, …, 8000) for each sample point in p i is estimated.
Ii) estimating the inverse cumulative distribution function value p n,i for the normal distribution of the standard at c k.
Step 3) calculating a covariance matrix sigma of P n={pn,1,pn,2,…,pn,69, and obtaining a lower triangular matrix L by adopting Cholesky decomposition.
Step 4) calculate the neural network training set input sample P t=L-1Pn T.
Step 5) generating a neural network test set input sample P s, specifically including:
i) Calculating standard deviation vector Wherein/>The ith row and the kth column of matrix L -1.
Ii) generating a random variable p c,i with a mean value of 0 and a standard deviation of sigma i, which obeys an independent normal distribution.
Iii) A test set input sample P s=L-1Pc T is obtained, where P c={pc,1,pc,2,…,pc,69.
Step 6) training the neural network by using the training set input sample and the node voltage amplitude sample.
And 7) inputting the test set input sample into a neural network to obtain a synthesized node voltage amplitude sample U s.
Step 8) calculating the maximum information coefficient between all node pairs, which specifically comprises the following steps:
i) And drawing a scatter diagram according to the node voltage amplitude samples of the two nodes i and j.
Ii) dividing the scatter diagram by grids with different rows and columns.
Iii) For a grid G with resolution of k rows and l columns, changing dividing positions of the grid, and calculating maximum mutual information I k,l((Ui,Uj),k,l)=maxI((Ui,Uj) G of the grid based on the resolution between two node voltage amplitude samples.
Iv) calculate normalized mutual information I * k,l=Ik,l((Ui,Uj) based on grid G with resolution k rows/columns, k, l)/logmin { k, l }.
V) forming a matrix M based on the normalized mutual information I * k,l of the grid of all resolutions, the kth row and the first column element of the matrix M being I * k,l.
Vi) the maximum information coefficient is the maximum element value in the matrix M.
Step 9) obtaining a topological structure by adopting a maximum spanning tree algorithm based on the maximum information coefficient, which comprises the following steps:
i) A graph T is built containing N nodes.
Ii) arranging all node pairs in the order of the maximum information coefficient of the voltage amplitude from large to small, wherein the ordered node pairs are represented by e k, k=1, 2, … and N (N-1)/2.
Iii) E 1 and e 2 are added to graph T.
Iv) let k=3.
V) when the number of edges in the graph T is smaller than N-1, performing steps vi) to viii), otherwise proceeding to step ix).
Vi) when e k is added to figure T, no ring is formed, then e k is added to figure T.
vii)k=k+1。
Viii) when k > N (N-1)/2, go to step ix), otherwise go to step v).
Ix) graph T is the topology identification result.
Compared with the prior art, the topology structure identification method effectively considers the influence of the output correlation of the distributed power supply, and obtains an accurate topology structure identification result of the power distribution network on the premise that the known power distribution network line parameters are not needed, the node injection power is not needed to be independent and the node voltage amplitude probability distribution is not needed to be assumed.
The foregoing embodiments may be partially modified in numerous ways by those skilled in the art without departing from the principles and spirit of the invention, the scope of which is defined in the claims and not by the foregoing embodiments, and all such implementations are within the scope of the invention.
Claims (4)
1. The power distribution network topological structure identification method considering the distributed power supply output correlation is characterized in that the preprocessed power grid data is used as a training set to train a neural network in an off-line stage, a synthesized node voltage amplitude sample is obtained through the training neural network input by a test set in an on-line stage, then the power distribution network topological structure identification is carried out by adopting a maximum spanning tree algorithm based on a maximum information coefficient, all node pairs of the power distribution network are obtained, each node pair represents one edge in the power distribution network topological structure and is used as a power distribution network topological structure identification result;
the power grid data is node injection power and node voltage amplitude measurement data of all nodes of the power grid;
The pretreatment is as follows: after the injection power measurement P i of the node i is converted into a random variable P n,i conforming to standard normal distribution, calculating a covariance matrix sigma of P n={pn,1,pn,2,…,pn,N, and then obtaining a lower triangular matrix L by adopting Cholesky decomposition to obtain an input sample P t=L-1Pn T of a neural network training set, wherein: i=1, 2, …, N;
the maximum spanning tree algorithm based on the maximum information coefficient specifically comprises the following steps:
i) Establishing a graph T containing N nodes;
ii) calculating the maximum information coefficient of all nodes to the voltage amplitude;
iii) Arranging all node pairs in the order of the maximum information coefficient of the voltage amplitude from large to small, wherein the ordered node pairs are represented by e k, k=1, 2, … and N (N-1)/2;
iv) adding e 1 and e 2 to map T;
v) set k=3;
vi) performing steps vii) to ix) when the number of edges in the graph T is less than N-1, otherwise proceeding to step x);
vii) when e k is added to graph T, no ring is formed, then e k is added to graph T;
viii)k=k+1;
ix) when k > N (N-1)/2, go to step x), otherwise go to step vi);
x) the obtained graph T is the topology identification result;
The maximum information coefficient is obtained by the following steps:
i) Drawing a scatter diagram according to the node voltage amplitude samples of the two nodes i and j;
ii) dividing the scatter diagram by grids with different rows and columns;
iii) For a grid G with resolution of k rows and l columns, changing dividing positions of the grid, and calculating maximum mutual information I k,l((Ui,Uj),k,l)=maxI((Ui,Uj) I G of the grid based on the resolution between two node voltage amplitude samples;
iv) calculating normalized mutual information I * k,l=Ik,l((Ui,Uj) based on a grid G with resolution of k rows and l columns, k, l)/logmin { k, l };
v) forming a matrix M based on normalized mutual information I * k,l of grids with all resolutions, wherein the element of the kth row and the first column of the matrix M is I * k,l;
vi) the maximum information coefficient is the maximum element value in the matrix M.
2. The method for identifying the topological structure of the power distribution network by considering the output correlation of the distributed power supply according to claim 1, wherein the training set refers to a set of training set input samples P t and training set output samples, namely node voltage amplitude measurement U t={u1,u2,…,uN;
the test set is obtained by the following steps:
1) Calculating standard deviation vector Wherein: /(I)The ith row and the kth column of matrix L -1;
2) Generating a random variable p c,i with a mean value of 0 and a standard deviation of sigma i, which obeys independent normal distribution;
3) A test set input sample P s=L-1Pc T is obtained, where P c={pc,1,pc,2,…,pc,N.
3. The method for identifying a topology of a power distribution network taking into account the correlation of distributed power output as recited in claim 1, wherein said neural network comprises: preprocessing module, input layer, hidden layer and output layer, wherein: the preprocessing module converts node voltage amplitude corresponding to the node injection power with correlation into node voltage amplitude corresponding to the independent node injection power;
the number of neurons of the input layer is node number minus 1, the number of hidden layers is 2, the number of neurons is 1000, and the number of neurons of the output layer is node number minus 1.
4. A system for implementing the method of any one of claims 1-3, comprising: the system comprises a data reading module, a preprocessing module, a synthesized node voltage amplitude generating module, a maximum spanning tree algorithm module and a result output module which are sequentially connected, wherein: the data reading module reads the node injection power and node voltage amplitude measurement data of the power distribution network; the preprocessing module generates a neural network training set and a test set sample according to the node injection power and the node voltage amplitude measurement data; the synthesized node voltage amplitude generating module obtains synthesized node voltage amplitude by adopting a neural network; the maximum spanning tree algorithm module obtains a maximum spanning tree according to the maximum information coefficient among the synthesized node voltage amplitudes; the result output module outputs the maximum spanning tree as a topology identification result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111551789.6A CN114169118B (en) | 2021-12-17 | 2021-12-17 | Power distribution network topological structure identification method considering distributed power output correlation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111551789.6A CN114169118B (en) | 2021-12-17 | 2021-12-17 | Power distribution network topological structure identification method considering distributed power output correlation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114169118A CN114169118A (en) | 2022-03-11 |
CN114169118B true CN114169118B (en) | 2024-06-21 |
Family
ID=80487286
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111551789.6A Active CN114169118B (en) | 2021-12-17 | 2021-12-17 | Power distribution network topological structure identification method considering distributed power output correlation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114169118B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115051474B (en) * | 2022-08-11 | 2023-01-13 | 国网江苏省电力有限公司泰州供电分公司 | Power distribution network line switch state identification method and system |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105225163A (en) * | 2014-06-25 | 2016-01-06 | 国家电网公司 | The reconstructing method of active distribution network and device |
CN107453351B (en) * | 2017-07-12 | 2020-12-11 | 河海大学 | Power distribution network operation topology identification method based on node injection power |
CN108683180B (en) * | 2018-05-07 | 2020-06-19 | 国网河南省电力公司电力科学研究院 | Three-phase low-voltage power distribution network topology reconstruction method |
CN110289613B (en) * | 2019-06-17 | 2022-12-02 | 湖南大学 | Sensitivity matrix-based power distribution network topology identification and line parameter identification method |
CN110190600B (en) * | 2019-06-21 | 2022-09-30 | 国网天津市电力公司 | Three-phase power distribution network topology identification method based on AMI measurement nearest neighbor regression |
CN110659693B (en) * | 2019-09-26 | 2024-03-01 | 国网湖南省电力有限公司 | K-nearest neighbor classification-based power distribution network rapid topology identification method, system and medium |
CN111654392A (en) * | 2020-05-11 | 2020-09-11 | 国网浙江省电力有限公司电力科学研究院 | Low-voltage distribution network topology identification method and system based on mutual information |
AU2020103195A4 (en) * | 2020-11-03 | 2021-01-14 | East China University Of Science And Technology | A Method for Detecting Vulnerability of Large-scale Power Grid Based On Complex Network |
-
2021
- 2021-12-17 CN CN202111551789.6A patent/CN114169118B/en active Active
Non-Patent Citations (2)
Title |
---|
Distributed Energy Resources Topology Identification via Graphical Modeling;Yang Weng 等;IEEE Transactions on Power Systems;20161115;全文 * |
基于AMI潮流匹配的中压配电网两阶段拓扑辨识;刘超 等;电力系统及其自动化学报;20200110(03);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114169118A (en) | 2022-03-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109842373B (en) | Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics | |
CN109871976B (en) | Clustering and neural network-based power quality prediction method for power distribution network with distributed power supply | |
Liu et al. | Wind power plant prediction by using neural networks | |
CN110570122B (en) | Offshore wind power plant reliability assessment method considering wind speed seasonal characteristics and current collection system element faults | |
CN109193635B (en) | Power distribution network topological structure reconstruction method based on self-adaptive sparse regression method | |
CN110070228B (en) | BP neural network wind speed prediction method for neuron branch evolution | |
CN109088407B (en) | Power distribution network state estimation method based on deep belief network pseudo-measurement modeling | |
CN111880044A (en) | Online fault positioning method for power distribution network with distributed power supply | |
CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
CN114169118B (en) | Power distribution network topological structure identification method considering distributed power output correlation | |
CN112883522A (en) | Micro-grid dynamic equivalent modeling method based on GRU (generalized regression Unit) recurrent neural network | |
CN113222250B (en) | High-power laser device output waveform prediction method based on convolutional neural network | |
CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
CN116247668A (en) | Power distribution network operation mode identification method based on measurement big data analysis | |
CN115544860A (en) | Output modeling method of intermittent distributed power supply in complex operation scene | |
Zhang et al. | Correntropy‐based parameter estimation for photovoltaic array model considering partial shading condition | |
CN115660893A (en) | Transformer substation bus load prediction method based on load characteristics | |
Shi et al. | A fault location method for distribution system based on one-dimensional convolutional neural network | |
CN114545147A (en) | Voltage sag source positioning method based on deep learning in consideration of time-varying topology | |
Moradzadeh et al. | Image processing-based data integrity attack detection in dynamic line rating forecasting applications | |
CN114676887A (en) | River water quality prediction method based on graph convolution STG-LSTM | |
CN114077849A (en) | Engine health state identification method based on component level fusion | |
CN111027816B (en) | Photovoltaic power generation efficiency calculation method based on data envelope analysis | |
Mahmoud et al. | Fault Location of Doukan-Erbil 132kv Double Transmission Lines Using Artificial Neural Network ANN | |
CN113962432A (en) | Wind power prediction method and system integrating three-dimensional convolution and light-weight convolution threshold unit |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |