CN109492866A - A kind of distribution Running State intelligent evaluation method - Google Patents
A kind of distribution Running State intelligent evaluation method Download PDFInfo
- Publication number
- CN109492866A CN109492866A CN201811167551.1A CN201811167551A CN109492866A CN 109492866 A CN109492866 A CN 109492866A CN 201811167551 A CN201811167551 A CN 201811167551A CN 109492866 A CN109492866 A CN 109492866A
- Authority
- CN
- China
- Prior art keywords
- running state
- distribution
- moment
- model
- intelligent evaluation
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 230000000306 recurrent effect Effects 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000013210 evaluation model Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims abstract description 6
- 230000001131 transforming effect Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 210000005036 nerve Anatomy 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000009466 transformation Effects 0.000 abstract description 2
- 241001269238 Data Species 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
A kind of distribution Running State intelligent evaluation method, the method obtains the electrical time series data of distribution transforming node, establish the distribution Running State intelligent evaluation model based on Recognition with Recurrent Neural Network, and it will predict that each node operating status amount is compared with actual motion quantity of state, reflect the operating status of each section of distribution network line, the validity that verifying model is assessed under each node time series data situation of change in real time by difference variable quantity.The present invention considers power distribution network time series data feature, and Recognition with Recurrent Neural Network is applied in distribution Running State intelligent evaluation, and compared with conventional neural networks, Recognition with Recurrent Neural Network can accurately reflect prediction distribution Running State.Distribution Running State intelligent evaluation model proposed by the present invention has stronger practicability, is typical case of the deep learning in terms of distribution Running State assessment, can overhaul for power distribution network O&M and technological transformation project project verification provides foundation.
Description
Technical field
The present invention relates to a kind of distribution Running State intelligent evaluation methods, belong to operation of power networks status assessment technical field.
Background technique
Accurate evaluation distribution Running State plays a significant role realization power distribution network safe operation.Power distribution network running environment
The defects of complexity, automatization level is lower, ageing equipment, loosening can cause distribution Running State to change, correspondingly
Distribution power flow redistribution, can effectively reflect distribution Running State by each node state amount situation of change.
For the problem that distribution network parameters missing and topology are complicated, a kind of distribution Running State of data-driven is proposed
Intelligent evaluation method is extended distribution network voltage sensitivity matrix, considers continuous historical metrology data of more periods, establishes
Suitable for the Recognition with Recurrent Neural Network temporal model of distribution Running State assessment, by prediction state of electric distribution network amount and virtual condition amount
It is compared, and then achievees the purpose that assess distribution Running State.The accuracy and validity of method in Example Verification text.
Summary of the invention
The object of the present invention is to for the prior art to problem existing for assessment distribution Running State, in order to solve to match
Operation of power networks status assessment problem, the present invention propose a kind of distribution Running State intelligent evaluation method of data-driven.
The technical solution that the present invention realizes is as follows: a kind of distribution Running State intelligent evaluation method, and the method obtains
The electrical time series data of distribution transforming node establishes the distribution Running State intelligent evaluation model based on Recognition with Recurrent Neural Network, and will be pre-
It surveys each node operating status amount to be compared with actual motion quantity of state, distribution network line is reflected by difference variable quantity in real time
The operating status of each section, the validity that verifying model is assessed under each node time series data situation of change.
A kind of distribution Running State intelligent evaluation method, steps are as follows:
(1) each node operation data of power distribution network, including active and reactive, voltage, electric current are acquired；
(2) otherness of prediction result when analyzing different Recognition with Recurrent Neural Network model trainings；
(3) according to model training as a result, choosing suitable Recognition with Recurrent Neural Network model as state estimator；
(4) predicted value is compared with practical each node voltage variable quantity, difference variable quantity is less than specific threshold, generally
Specific threshold takes 0.1Kv, then it is assumed that distribution Running State is normal；If more than specific threshold, then it is assumed that distribution Running State
It is abnormal.
The Recognition with Recurrent Neural Network model, can input to each moment and to combine the state of "current" model to provide corresponding defeated
Out, by reading the input x at t-1 moment, and a h is exported, the state of "current" model can be transmitted to next from the current t-1 moment
Moment t；Therefore, for one group of time series data, the data of different moments are successively passed to the input layer of circulation nerve, output in sequence
It can be the prediction to sequence subsequent time, be also possible to the processing result to current time information.
It is assumed that t moment list entries is xt, model state ht-1, output sequence ot, respective formula is as follows:
at=Uxt+Wht-1+ b,
ht=e (at)；
ot=Vht+c；
yt=g (ot)
Wherein, b and c is bias vector；U, V, W be respectively be input to it is hiding, be hidden into output and be hidden into hiding company
Matrix is connect, error function can be mean square deviation or intersect entropy function；atResult is exported for t moment input layer to hidden layer；htFor t
Moment model state exports result；OtResult is exported for t moment hidden layer to output layer；ytFor t moment final output.
The model training parameter is as follows: learning rate 0.001, the number of iterations 1000, and list entries window is 5, often
A moment input quantity ties up active and idle data for 66, exports and ties up voltage varieties for 33, and the first the number of hidden nodes is 66, the
Two, three layers are LSTM layers, number of nodes 66, the 4th layer of the number of hidden nodes 33, and cost function selects mean square error function.
The invention has the advantages that the problem that the present invention is lacked for distribution network parameters and topology is complicated, proposes one kind
The distribution Running State intelligent evaluation method of data-driven.The present invention considers power distribution network time series data feature, by circulation nerve
Network application is in distribution Running State intelligent evaluation, and compared with conventional neural networks, Recognition with Recurrent Neural Network can be accurate
Reflect prediction distribution Running State.Distribution Running State intelligent evaluation model proposed by the present invention has stronger practical
Property, it is typical case of the deep learning in terms of distribution Running State assessment, can is the maintenance of power distribution network O&M and technological transformation item
Mesh project verification provides foundation.
Detailed description of the invention
Fig. 1 is distribution Running State intelligent evaluation model flow figure；
Fig. 2 is 33 node connection figure of power distribution network IEEE；
Fig. 3 is Recognition with Recurrent Neural Network structure chart；
Fig. 4 is 31 node voltage variable quantity difference under normal circumstances；
Fig. 5 is 31 node voltage variable quantity differences under abnormal conditions.
Specific embodiment
A specific embodiment of the invention is as shown in Figure 1.
The present invention is embodied as follows so that certain saves power distribution network operation as an example:
(1) data are acquired
Example is IEEE33 node system, and the voltage rating of bus is 12.66kV, there is 33 nodes, 37 branches, wiring
Figure as shown in Fig. 2, 33 nodes are active and reactive, voltage data is derived from 33 distribution transforming node operation datas of Jiangxi company line,
30min is divided between data sampling, 7000 normal condition data are used for model training, and 180 normal condition data are used to verify,
For predicting, input data is that each node is active and reactive for 820 normal condition data and 820 abnormality data, exports number
According to for each node voltage states variable quantity.
(2) Recognition with Recurrent Neural Network model foundation
Traditional neural network can not be using the time serial message in power distribution network monitoring data, in processing dynamic time sequence data
When, often due to a lack of dynamic behavior abundant and expression effect is not good enough, and in Recognition with Recurrent Neural Network mining data timing letter
Breath is fully utilized, in different time points shared parameter, does not need to distribute a list to each feature as full connection feedforward network
Only parameter, enables model to expand to various forms of samples, and Recognition with Recurrent Neural Network model is as shown in Figure 3.
Recognition with Recurrent Neural Network input to each moment and can combine the state of "current" model to provide corresponding output, pass through reading
The input x at t-1 moment is taken, and exports a h, the state of "current" model can be transmitted to subsequent time t from the current t-1 moment.Cause
This, for one group of time series data, the data of different moments are successively passed to the input layer of circulation nerve in sequence, and output can be pair
The prediction of sequence subsequent time is also possible to the processing result to current time information.It is assumed that t moment list entries is xt, mould
Type state is ht-1, output sequence ot, respective formula is as follows:
at=Uxt+Wht-1+b (1)
ht=e (at) (2)
ot=Vht+c (3)
yt=g (ot) (4)
Wherein: b and c is bias vector, U, V, W be respectively be input to it is hiding, be hidden into output and be hidden into hiding company
Matrix is connect, error function can be mean square deviation or intersect entropy function；atResult is exported for t moment input layer to hidden layer；htFor t
Moment model state exports result；OtResult is exported for t moment hidden layer to output layer；ytFor t moment final output.
(3) model training
Distribution transformer is active and reactive, voltage data is derived from 33 distribution transforming node operation datas of Jiangxi company line, number
It is 30min according to the sampling interval, 7000 normal condition data are used for model training, and 180 normal condition data are used to verify,
For predicting, input data is that each node is active and reactive for 820 normal condition data and 820 abnormality data, exports number
According to for each node voltage states variable quantity.
LSTM Recognition with Recurrent Neural Network training parameter is as follows, learning rate 0.001, the number of iterations 1000, list entries window
Mouth is 5, and each moment input quantity ties up active and idle data for 66, is exported as 33 dimension voltage varieties, the first the number of hidden nodes
It is 66, second and third layer is LSTM layers, number of nodes 66, the 4th layer of the number of hidden nodes 33, and cost function selects mean square error letter
Number.
(4) status assessment
By taking 30 nodes to 31 node line sections as an example, when operating status is normal, as shown in figure 4, with 820 time series datas
Prediction comparison result can be seen that 30 nodes, voltage prediction assessed value and reality steady to 31 node sectionalized line operating statuses
Voltage variety difference is maintained at a constant 0 and nearby fluctuates, and fluctuating range is no more than 0.05kV, is consistent with actual conditions.
When 30 nodes to 31 node line operation by sections abnormal state, as shown in figure 5, voltage prediction assessed value and practical electricity
Pressure variable quantity difference curve fluctuates widely, and fluctuating range is more than 0.1kV, illustrates that track section operating status is abnormal, with
Practical track section impedance increase etc. is related, needs especially to pay close attention to.
Claims (5)
1. a kind of distribution Running State intelligent evaluation method, which is characterized in that the method obtains the electrical timing of distribution transforming node
Data establish the distribution Running State intelligent evaluation model based on Recognition with Recurrent Neural Network, and will predict each node operating status
Amount is compared with actual motion quantity of state, reflects the operation shape of each section of distribution network line in real time by difference variable quantity
State, the validity that verifying model is assessed under each node time series data situation of change.
2. a kind of distribution Running State intelligent evaluation method according to claim 1, which is characterized in that the method step
It is rapid as follows:
(1) each node operation data of power distribution network, including active and reactive, voltage, electric current are acquired；
(2) otherness of prediction result when analyzing different Recognition with Recurrent Neural Network model trainings；
(3) according to model training as a result, choosing suitable Recognition with Recurrent Neural Network model as state estimator；
(4) predicted value is compared with practical each node voltage variable quantity, difference variable quantity is less than specific threshold, general specific
Threshold values takes 0.1Kv, then it is assumed that distribution Running State is normal；If more than specific threshold, then it is assumed that distribution Running State is abnormal.
3. a kind of distribution Running State intelligent evaluation method according to claim 1, which is characterized in that the circulation mind
Through network model, input to each moment and the state of "current" model can be combined to provide corresponding output, pass through and read the t-1 moment
Input x, and export a h, the state of "current" model can be transmitted to subsequent time t from the current t-1 moment；Therefore, for one
Group time series data, the data of different moments are successively passed to the input layer of circulation nerve in sequence, and output can be under sequence one
The prediction at moment is also possible to the processing result to current time information；
It is assumed that t moment list entries is xt, model state ht-1, output sequence ot, respective formula is as follows:
at=Uxt+Wht-1+ b,
ht=e (at)；
ot=Vht+c；
yt=g (ot)
Wherein, b and c is bias vector；U, V, W be respectively be input to it is hiding, be hidden into output and be hidden into hiding connection square
Battle array, error function can be mean square deviation or intersect entropy function；atResult is exported for t moment input layer to hidden layer；htFor t moment
Model state exports result；otResult is exported for t moment hidden layer to output layer；ytFor t moment final output.
4. a kind of distribution Running State intelligent evaluation method according to claim 2, which is characterized in that the model instruction
It is as follows to practice parameter: learning rate 0.001, the number of iterations 1000, list entries window are 5, and each moment input quantity is 66 dimensions
Active and idle data export and tie up voltage varieties for 33, and the first the number of hidden nodes is 66, second and third layer is LSTM layers, node
Number is 66, and the 4th layer of the number of hidden nodes 33, cost function selects mean square error function.
5. a kind of distribution Running State intelligent evaluation method according to claim 2, which is characterized in that the operation shape
State assessment is as follows:
Voltage prediction assessed value and virtual voltage variable quantity difference are maintained at a constant 0 and nearby fluctuate, and fluctuating range is no more than
0.05kV is consistent with actual conditions；
Voltage prediction assessed value fluctuates widely with virtual voltage variable quantity difference curve, and fluctuating range is more than 0.1kV, says
Open-wire line road operation by sections abnormal state, it is related with practical track section impedance increase etc., it needs especially to pay close attention to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811167551.1A CN109492866A (en) | 2018-10-08 | 2018-10-08 | A kind of distribution Running State intelligent evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811167551.1A CN109492866A (en) | 2018-10-08 | 2018-10-08 | A kind of distribution Running State intelligent evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109492866A true CN109492866A (en) | 2019-03-19 |
Family
ID=65690208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811167551.1A Pending CN109492866A (en) | 2018-10-08 | 2018-10-08 | A kind of distribution Running State intelligent evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492866A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333697A (en) * | 2019-03-20 | 2019-10-15 | 广西壮族自治区机械工业研究院 | A kind of internet of things data acquisition analysis system applied to high-pressure wash machine people |
| CN110457770A (en) * | 2019-07-18 | 2019-11-15 | 中国电力科学研究院有限公司 | A kind of distribution transformer heavy-overload judgment method towards time scale |
| CN110501585A (en) * | 2019-07-12 | 2019-11-26 | 武汉大学 | A kind of Diagnosis Method of Transformer Faults based on Bi-LSTM and dissolved gas analysis |
| CN112001295A (en) * | 2020-08-19 | 2020-11-27 | 北京航天飞行控制中心 | Performance evaluation method and device for high-speed rotor shafting, storage medium and processor |
| CN112819373A (en) * | 2021-02-25 | 2021-05-18 | 云南电网有限责任公司电力科学研究院 | Distribution network voltage abnormal data detection method and device |
| CN113393102A (en) * | 2021-06-02 | 2021-09-14 | 重庆大学 | Distribution transformer operation state trend prediction method based on data driving |
| CN113762716A (en) * | 2021-07-30 | 2021-12-07 | 国网山东省电力公司营销服务中心(计量中心) | Method and system for evaluating running state of transformer area based on deep learning and attention |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105633956A (en) * | 2016-02-19 | 2016-06-01 | 河海大学 | Spiking neural network pseudo measurement modeling based three-phase state estimation method for power distribution network |
| CN106656637A (en) * | 2017-02-24 | 2017-05-10 | 国网河南省电力公司电力科学研究院 | Anomaly detection method and device |
| US20170293542A1 (en) * | 2016-04-06 | 2017-10-12 | Nec Laboratories America, Inc. | System failure prediction using long short-term memory neural networks |
| CN108090556A (en) * | 2017-12-22 | 2018-05-29 | 国网江西省电力有限公司电力科学研究院 | A kind of hot appraisal procedure of distribution transformer |
-
2018
- 2018-10-08 CN CN201811167551.1A patent/CN109492866A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105633956A (en) * | 2016-02-19 | 2016-06-01 | 河海大学 | Spiking neural network pseudo measurement modeling based three-phase state estimation method for power distribution network |
| US20170293542A1 (en) * | 2016-04-06 | 2017-10-12 | Nec Laboratories America, Inc. | System failure prediction using long short-term memory neural networks |
| CN106656637A (en) * | 2017-02-24 | 2017-05-10 | 国网河南省电力公司电力科学研究院 | Anomaly detection method and device |
| CN108090556A (en) * | 2017-12-22 | 2018-05-29 | 国网江西省电力有限公司电力科学研究院 | A kind of hot appraisal procedure of distribution transformer |
Non-Patent Citations (1)
| Title |
|---|
| 高志强，黄剑，李永，刘明明: "《深度学习 从入门到实战》", 30 June 2018 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333697A (en) * | 2019-03-20 | 2019-10-15 | 广西壮族自治区机械工业研究院 | A kind of internet of things data acquisition analysis system applied to high-pressure wash machine people |
| CN110501585A (en) * | 2019-07-12 | 2019-11-26 | 武汉大学 | A kind of Diagnosis Method of Transformer Faults based on Bi-LSTM and dissolved gas analysis |
| CN110457770A (en) * | 2019-07-18 | 2019-11-15 | 中国电力科学研究院有限公司 | A kind of distribution transformer heavy-overload judgment method towards time scale |
| CN110457770B (en) * | 2019-07-18 | 2022-07-01 | 中国电力科学研究院有限公司 | Time scale-oriented overload judgment method for distribution transformer |
| CN112001295A (en) * | 2020-08-19 | 2020-11-27 | 北京航天飞行控制中心 | Performance evaluation method and device for high-speed rotor shafting, storage medium and processor |
| CN112001295B (en) * | 2020-08-19 | 2023-12-08 | 北京航天飞行控制中心 | Performance evaluation method and device of high-speed rotor shaft system, storage medium and processor |
| CN112819373A (en) * | 2021-02-25 | 2021-05-18 | 云南电网有限责任公司电力科学研究院 | Distribution network voltage abnormal data detection method and device |
| CN113393102A (en) * | 2021-06-02 | 2021-09-14 | 重庆大学 | Distribution transformer operation state trend prediction method based on data driving |
| CN113393102B (en) * | 2021-06-02 | 2022-08-12 | 重庆大学 | Distribution transformer operation state trend prediction method based on data driving |
| CN113762716A (en) * | 2021-07-30 | 2021-12-07 | 国网山东省电力公司营销服务中心(计量中心) | Method and system for evaluating running state of transformer area based on deep learning and attention |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492866A (en) | A kind of distribution Running State intelligent evaluation method | |
| Jiang et al. | Stochastic subspace identification‐based approach for tracking inter‐area oscillatory modes in bulk power system utilising synchrophasor measurements | |
| CN102663412A (en) | Power equipment current-carrying fault trend prediction method based on least squares support vector machine | |
| CN112051481A (en) | Alternating current-direct current hybrid power grid fault area diagnosis method and system based on LSTM | |
| CN107276072B (en) | Method for quantitatively evaluating transient stability margin of power system by using steady state information | |
| CN105322519A (en) | Big data fusion analysis and running state monitoring method for intelligent power distribution network | |
| CN112070413B (en) | Reliability research method of traction power supply system based on small sample condition | |
| CN111798095A (en) | Power cable state evaluation method based on neural network | |
| CN111814849A (en) | DA-RNN-based wind turbine generator key component fault early warning method | |
| CN111931849A (en) | Hydroelectric generating set operation data trend early warning method | |
| CN105699849A (en) | Voltage sag estimation method based on quantum-behaved particle swarm optimization algorithm | |
| CN114252694A (en) | System and method for monitoring energy related data in an electrical system | |
| CN111209535B (en) | Power equipment successive fault risk identification method and system | |
| Baruzzi et al. | Analysis and improvement of an algorithm for the online inertia estimation in power grids with RES | |
| CN109726880B (en) | Power transmission line parameter rationality assessment method and system | |
| Zhang et al. | Low frequency oscillation mode estimation using synchrophasor data | |
| Hassani et al. | Design of a cost-effective deep convolutional neural network–based scheme for diagnosing faults in smart grids | |
| Yusuf et al. | Predicting Voltage Changes in Low-Voltage Secondary Networks using Deep Neural Networks | |
| Xue et al. | An efficient and robust case sorting algorithm for transient stability assessment | |
| CN113991652B (en) | Data-driven multi-output calculation method for short-circuit current of distribution network containing IIDG | |
| CN113627655B (en) | Method and device for simulating and predicting pre-disaster fault scene of power distribution network | |
| CN114861969A (en) | LSTM-based electric power system oscillation risk prediction method | |
| Zhu et al. | Cross-Domain Data Fusion On Distribution Network Voltage Estimation with DS Evidence Theory | |
| CN113537338A (en) | Robust line parameter identification method based on LSTM neural network and improved SCADA data | |
| CN113537821A (en) | Rapid assessment method and system for state of 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190319 |