CN114169118A - Power distribution network topological structure identification method considering distributed power supply output correlation - Google Patents
Power distribution network topological structure identification method considering distributed power supply output correlation Download PDFInfo
- Publication number
- CN114169118A CN114169118A CN202111551789.6A CN202111551789A CN114169118A CN 114169118 A CN114169118 A CN 114169118A CN 202111551789 A CN202111551789 A CN 202111551789A CN 114169118 A CN114169118 A CN 114169118A
- Authority
- CN
- China
- Prior art keywords
- node
- distribution network
- voltage amplitude
- power distribution
- power
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 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 17
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 238000005259 measurement Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000005315 distribution function Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 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
- 238000005516 engineering process Methods 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
Images
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)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
A power distribution network topological structure identification method considering the output correlation of a distributed power supply includes the steps that preprocessed power grid data serve as a training set to train a neural network in an off-line stage, a test set is used for inputting the trained neural network to obtain a synthesized node voltage amplitude sample in an on-line stage, then a maximum spanning tree algorithm based on a maximum information coefficient is adopted to conduct power distribution network topological structure identification, all node pairs of a power distribution network are obtained, and each node pair represents one edge in the power distribution network topological structure and serves as a power distribution network topological structure identification result. The invention adopts a neural network to establish the relation between the node voltage amplitude and the node injection power, and provides a maximum spanning tree algorithm based on the 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 devices such as a generator, a distributed power supply, a load and the like; the edges of the graph represent lines in the grid. The topological structure of the power system describes the connection relation among nodes in the power grid, and is an important basis for analysis and application of power system optimization operation, fault location, power failure management and the like. Generally, the operator of the power system can accurately solve the topology of the power transmission network, and only needs to identify the error of the topology according to the relatively complete measurement information. However, due to numerous nodes and branches of the power distribution network, measurement information is incomplete, and the topology structure changes frequently, and particularly, under the background that the distributed power supply is accessed to the power distribution network in a large scale, the topology structure of the power distribution network is difficult to accurately know.
With the large-scale deployment of an Advanced Measurement Infrastructure (AMI) And a data acquisition And monitoring Control System (SCADA), node voltage amplitude And injection power measurement information can be acquired, And the information has important value for identifying a topological structure. The existing power distribution network topological structure method depends on certain assumed conditions, such as known power distribution network line parameters, independent node injection power, node voltage obeying normal distribution and the like.
Disclosure of Invention
Aiming at the defects of the existing 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 identifying the power distribution network topological structure.
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.
The power grid data refer to node injection power and node voltage amplitude measurement data of all nodes of the power distribution network.
The pretreatment is as follows: measure p the injection power of node iiConversion to a random variable p obeying a standard normal distributionn,iThen, P is calculatedn={pn,1,pn,2,…,pn,NAnd (4) obtaining a lower triangular matrix L by using Cholesky decomposition to obtain an input sample P of the neural network training sett=L-1Pn TWherein: i is 1,2, …, N.
The training set is a training set input sample PtAnd training set output samples, i.e. node voltage amplitude measurement Ut={u1,u2,…,uNThe set of (c).
The test set is obtained by the following steps:
2) The mean value is 0 and the standard deviation is sigmaiIs subject to an independent normal distributionc,i。
3) Obtaining a test set input sample Ps=L-1Pc TIn which P isc={pc,1,pc,2,…,pc,N}。
The neural network comprises: 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 the correlation into the node voltage amplitude corresponding to the independent node injection power.
The number of neurons of the input layer is the number of nodes minus 1, the number of layers of the hidden layer is 2, the number of neurons is 1000, and the number of neurons of the output layer is the number of nodes minus 1.
The maximum spanning tree algorithm based on the maximum information coefficient specifically includes:
i) a graph T is established containing N nodes.
ii) calculating the maximum information coefficient of the voltage amplitude of all the nodes.
iii) arranging all node pairs in the order of maximum voltage amplitude information coefficient from large to small, and using e for the ordered node pairskAnd k is 1,2, …, N (N-1)/2.
iv) mixing e1And e2Add panel T.
v) setting k to 3.
vi) when the number of edges in the graph T is less than N-1, performing steps vii) to ix), otherwise go to step x):
vii) when e is equal tokAfter adding graph T, if no ring is formed, e is addedkAdd panel T.
viii)k=k+1。
ix) when k is larger than N (N-1)/2, go to step x), otherwise go to step vi).
x) obtaining a graph T which is the result of the topology identification.
The invention relates to a system for realizing the method, which comprises the following steps: the data reading module, the preprocessing module, the synthesized node voltage amplitude generation module, the maximum spanning tree algorithm module and the result output module are connected in sequence, wherein: the data reading module reads measurement data of the node injection power and the node voltage amplitude 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 generation module obtains a 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 between the synthesized node voltage amplitudes; and the result output module outputs the maximum spanning tree as a topology identification result.
Technical effects
According to the invention, the normal distribution property is utilized, the neural network input sets which obey different distributions are converted into the input sets which obey the same distribution through cumulative distribution function transformation, the coverage range of the training sample input set is ensured to contain the test sample input set, the training precision of the neural network is improved, and meanwhile, the maximum information coefficient is adopted to accurately calculate the measurement correlation of the node voltage amplitude by the maximum spanning tree algorithm based on the maximum information coefficient, so that the precision of the topological structure identification algorithm is improved. Compared with the prior art, the topological structure identification method effectively accounts for the influence of the output correlation of the distributed power supply, and obtains an accurate distribution network topological structure identification result on the premise of not needing to know the line parameters of the distribution network, not needing to assume that the node injection powers are mutually independent and not needing to assume node voltage amplitude probability distribution.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a system wiring diagram of an embodiment IEEE 69 node;
FIG. 3 is a schematic diagram illustrating the effects of the embodiment.
Detailed Description
As shown in fig. 2, in this embodiment, an IEEE 69 node standard system is used as an example, node injection power measurement data disclosed by an actual power distribution network is used, a sampling scale is set to 8000, a neural network used in this embodiment is a fully-connected neural network, and includes 2 hidden layers, the number of neurons in the hidden layers is 1000, an Adam optimizer and a root-mean-square loss function are used, and a learning rate is set to 5 e-4.
The embodiment specifically comprises the following steps:
step 1) acquiring power grid data and acquiring a node injection power measurement sample pi(i-1, 2, …, 69) and a node voltage magnitude measurement sample ui(i=1,2,…,69)。piAnd uiAre vectors with dimensions 8000.
Step 2) adding piConversion to a random variable p obeying a standard normal distributionn,iThe method specifically comprises the following steps:
i) estimate piCumulative distribution function value c of each sample point ink(k=1,2,…,8000)。
ii) estimating the standard normal distribution at ckThe inverse cumulative distribution function value p ofn,i。
Step 3) calculating Pn={pn,1,pn,2,…,pn,69And (4) decomposing the covariance matrix sigma by Cholesky to obtain a lower triangular matrix L.
Step 4) calculating input sample P of neural network training sett=L-1Pn T。
Step 5) generating input sample P of neural network test setsThe method specifically comprises the following steps:
ii) mean 0 and standard deviation σ are generatediIs subject to an independent normal distributionc,i。
iii) obtaining a test set input sample Ps=L-1Pc TIn which P isc={pc,1,pc,2,…,pc,69}。
And 6) training the neural network by adopting the input samples of the training set and the node voltage amplitude samples.
Step 7) inputting the test set input sample into a neural network to obtain a synthesized node voltage amplitude sample Us。
Step 8) calculating the maximum information coefficient among 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) the scatter diagram is divided by grids of different row and column numbers.
iii) for the grid G with the resolution ratio of k rows and l columns, changing the division position of the grid, and calculating the maximum mutual information I between the voltage amplitude samples of the two nodes based on the grid with the resolution ratiok,l((Ui,Uj),k,l)=maxI((Ui,Uj)|G)。
iv) calculating based onNormalized mutual information I of grid G with resolution of k rows and l columns* k,l=Ik,l((Ui,Uj),k,l)/logmin{k,l}。
v) normalized mutual information I of the grid based on all resolutions* k,lForming a matrix M with the k row and l column elements of I* k,l。
vi) the largest information coefficient is the largest element value in the matrix M.
Step 9) obtaining a topological structure by adopting a maximum spanning tree algorithm based on a maximum information coefficient, and specifically comprises the following steps:
i) a graph T is established containing N nodes.
ii) arranging all node pairs in the order of maximum voltage amplitude information coefficient from large to small, and using e for the ordered node pairskAnd k is 1,2, …, N (N-1)/2.
iii) reacting e1And e2Add panel T.
iv) let k equal 3.
v) when the number of edges in the graph T is less than N-1, executing steps vi) to viii), otherwise, turning to step ix).
vi) when e is equal tokAfter adding graph T, if no ring is formed, e is addedkAdd panel 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 result of topology identification.
Compared with the prior art, the topological structure identification method effectively accounts for the influence of the output correlation of the distributed power supply, and obtains an accurate distribution network topological structure identification result on the premise of not needing to know the line parameters of the distribution network, not needing to assume that the node injection powers are mutually independent and not needing to assume node voltage amplitude probability distribution.
The foregoing embodiments may be modified in many different ways by those skilled in the art without departing from the spirit and scope of the invention, which is defined by the appended claims and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (5)
1. A power distribution network topological structure identification method considering the output correlation of a distributed power supply is characterized in that preprocessed power grid data are used as a training set to train a neural network in an off-line stage, a test set is used to input the trained neural network to obtain a synthesized node voltage amplitude sample in an on-line stage, then a maximum spanning tree algorithm based on a maximum information coefficient is adopted to carry out power distribution network topological structure identification to obtain all node pairs of the power distribution network, each node pair represents one edge in the power distribution network topological structure and serves as a power distribution network topological structure identification result;
the power grid data refer to node injection power and node voltage amplitude measurement data of all nodes of the power distribution network;
the pretreatment is as follows: measure p the injection power of node iiConversion to a random variable p obeying a standard normal distributionn,iThen, P is calculatedn={pn,1,pn,2,…,pn,NAnd (4) obtaining a lower triangular matrix L by using Cholesky decomposition to obtain an input sample P of the neural network training sett=L-1Pn TWherein: i is 1,2, …, N.
2. The method of claim 1, wherein the training set is a training set input sample PtAnd training set output samples, i.e. node voltage amplitude measurement Ut={u1,u2,…,uNA set of { fraction };
the test set is obtained by the following steps:
2) the mean value is 0 and the standard deviation is sigmaiIs subject to an independent normal distributionc,i;
3) Obtaining a test set input sample Ps=L-1Pc TIn which P isc={pc,1,pc,2,…,pc,N}。
3. The method of claim 1, wherein the neural network comprises: 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 the correlation into the node voltage amplitude corresponding to the independent node injection power;
the number of neurons of the input layer is the number of nodes minus 1, the number of layers of the hidden layer is 2, the number of neurons is 1000, and the number of neurons of the output layer is the number of nodes minus 1.
4. The method for identifying a power distribution network topology structure considering distributed power output correlations as claimed in claim 1, wherein the maximum spanning tree algorithm based on the maximum information coefficient specifically comprises:
i) establishing a graph T containing N nodes;
ii) calculating the maximum information coefficient of the voltage amplitude of all the nodes;
iii) arranging all node pairs in the order of maximum voltage amplitude information coefficient from large to small, and using e for the ordered node pairskK is 1,2, …, N (N-1)/2;
iv) mixing e1And e2Adding a graph T;
v) setting k to 3;
vi) when the number of edges in the graph T is less than N-1, executing steps vii) to ix), otherwise, turning to step x);
vii) when e is equal tokAfter adding graph T, if no ring is formed, e is addedkAdding a graph T;
viii)k=k+1;
ix) when k is larger than N (N-1)/2, go to step x), otherwise go to step vi);
x) obtaining a graph T which is the result of the topology identification.
5. A system for implementing the method of any one of claims 1 to 4, comprising: the data reading module, the preprocessing module, the synthesized node voltage amplitude generation module, the maximum spanning tree algorithm module and the result output module are connected in sequence, wherein: the data reading module reads measurement data of the node injection power and the node voltage amplitude 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 generation module obtains a 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 between the synthesized node voltage amplitudes; and 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 CN114169118A (en) | 2021-12-17 | 2021-12-17 | Power distribution network topological structure identification method considering distributed power supply output correlation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111551789.6A CN114169118A (en) | 2021-12-17 | 2021-12-17 | Power distribution network topological structure identification method considering distributed power supply output correlation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114169118A true CN114169118A (en) | 2022-03-11 |
Family
ID=80487286
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111551789.6A Pending CN114169118A (en) | 2021-12-17 | 2021-12-17 | Power distribution network topological structure identification method considering distributed power supply output correlation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114169118A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115051474A (en) * | 2022-08-11 | 2022-09-13 | 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 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015196743A1 (en) * | 2014-06-25 | 2015-12-30 | 国家电网公司 | Active distribution network reconfiguration method and apparatus |
CN108683180A (en) * | 2018-05-07 | 2018-10-19 | 国网河南省电力公司电力科学研究院 | A kind of three-phase low-voltage power distribution network topology rebuilding method |
CN110190600A (en) * | 2019-06-21 | 2019-08-30 | 国网天津市电力公司 | It is a kind of to measure the three-phase distribution net topology discrimination method that neighbour returns based on AMI |
CN110289613A (en) * | 2019-06-17 | 2019-09-27 | 湖南大学 | The identification of distribution net topology and line parameter circuit value discrimination method based on sensitivity matrix |
CN110659693A (en) * | 2019-09-26 | 2020-01-07 | 国网湖南省电力有限公司 | K-nearest neighbor classification-based rapid topology identification method and system for power distribution network and readable storage 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/CN114169118A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015196743A1 (en) * | 2014-06-25 | 2015-12-30 | 国家电网公司 | Active distribution network reconfiguration method and apparatus |
CN108683180A (en) * | 2018-05-07 | 2018-10-19 | 国网河南省电力公司电力科学研究院 | A kind of three-phase low-voltage power distribution network topology rebuilding method |
CN110289613A (en) * | 2019-06-17 | 2019-09-27 | 湖南大学 | The identification of distribution net topology and line parameter circuit value discrimination method based on sensitivity matrix |
CN110190600A (en) * | 2019-06-21 | 2019-08-30 | 国网天津市电力公司 | It is a kind of to measure the three-phase distribution net topology discrimination method that neighbour returns based on AMI |
CN110659693A (en) * | 2019-09-26 | 2020-01-07 | 国网湖南省电力有限公司 | K-nearest neighbor classification-based rapid topology identification method and system for power distribution network and readable storage 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 |
Non-Patent Citations (2)
Title |
---|
YANG WENG 等: "Distributed Energy Resources Topology Identification via Graphical Modeling", IEEE TRANSACTIONS ON POWER SYSTEMS, 15 November 2016 (2016-11-15) * |
刘超 等: "基于AMI潮流匹配的中压配电网两阶段拓扑辨识", 电力系统及其自动化学报, no. 03, 10 January 2020 (2020-01-10) * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115051474A (en) * | 2022-08-11 | 2022-09-13 | 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 |
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 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Menke et al. | Distribution system monitoring for smart power grids with distributed generation using artificial neural networks | |
Liu et al. | Wind power plant prediction by using neural networks | |
CN109842373B (en) | Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics | |
CN112051481B (en) | Alternating current-direct current hybrid power grid fault area diagnosis method and system based on LSTM | |
CN109462257B (en) | Sensitivity identification method considering voltage stability of multivariate random variable power grid | |
CN109193635B (en) | Power distribution network topological structure reconstruction method based on self-adaptive sparse regression method | |
CN111478314B (en) | Transient stability evaluation method for power system | |
Gilanifar et al. | Multi-task logistic low-ranked dirty model for fault detection in power distribution system | |
CN109472097B (en) | Fault diagnosis method for online monitoring equipment of power transmission line | |
CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
CN112507479B (en) | Oil drilling machine health state assessment method based on manifold learning and softmax | |
CN112883522A (en) | Micro-grid dynamic equivalent modeling method based on GRU (generalized regression Unit) recurrent neural network | |
Chen et al. | Data-driven robust state estimation through off-line learning and on-line matching | |
CN111122811A (en) | Sewage treatment process fault monitoring method of OICA and RNN fusion model | |
CN108520310A (en) | Wind speed forecasting method based on G-L mixed noise characteristic v- support vector regressions | |
CN112596016A (en) | Transformer fault diagnosis method based on integration of multiple one-dimensional convolutional neural networks | |
CN114169118A (en) | Power distribution network topological structure identification method considering distributed power supply output correlation | |
Ibrahim et al. | Novel data compression technique for power waveforms using adaptive fuzzy logic | |
Mudronja et al. | Data-based modelling of significant wave height in the Adriatic sea | |
CN113609749B (en) | Current calculation method applicable to multiple scenes and based on magnetic field signals | |
Liu et al. | Spatio-temporal generative adversarial network based power distribution network state estimation with multiple time-scale measurements | |
CN113901622A (en) | Genetic algorithm optimization-based SVM power distribution network topology identification method | |
CN115544860A (en) | Output modeling method of intermittent distributed power supply in complex operation scene | |
Comden et al. | Sample complexity of power system state estimation using matrix completion | |
CN115035962A (en) | Variational self-encoder and generation countermeasure network-based virtual sample generation and soft measurement modeling method |
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 |