CN112784215B - Wind power plant theoretical generating capacity calculation method based on real-time power remote measurement - Google Patents
Wind power plant theoretical generating capacity calculation method based on real-time power remote measurement Download PDFInfo
- Publication number
- CN112784215B CN112784215B CN202110083075.0A CN202110083075A CN112784215B CN 112784215 B CN112784215 B CN 112784215B CN 202110083075 A CN202110083075 A CN 202110083075A CN 112784215 B CN112784215 B CN 112784215B
- Authority
- CN
- China
- Prior art keywords
- power
- real
- wind turbine
- error
- calculating
- 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
- 238000005259 measurement Methods 0.000 title claims abstract description 20
- 238000004364 calculation method Methods 0.000 title description 9
- 238000000034 method Methods 0.000 claims abstract description 87
- 238000013213 extrapolation Methods 0.000 claims abstract description 63
- 239000002245 particle Substances 0.000 claims description 48
- 238000004891 communication Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Physiology (AREA)
- Mathematical Optimization (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Public Health (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Algebra (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
Abstract
The invention discloses a method for calculating theoretical generated energy of a wind power plant based on real-time power remote measurement, which comprises the following steps of: obtaining remote measurement of real-time active power of the wind turbine generator; calculating to obtain the power error of the sample board machine; calculating to obtain a power error of a power curve extrapolation method; predicting the power error of the sample plate machine and the power error of a power curve extrapolation method by using an LSTM model; carrying out weighted summation on the active power of the sample board machine and the active power of the power curve extrapolation method to obtain reference power; and integrating the reference power serving as the basis of the theoretical generating capacity statistics of the wind turbine generator set to obtain the theoretical generating capacity of the wind turbine generator set. The method determines the weight according to the power errors of the sample board machine and the power curve extrapolation method, performs weighted summation on the active power of the sample board machine and the power curve extrapolation method, and takes the obtained reference power as the integral basis of the theoretical generated energy of the wind turbine generator so as to obtain the theoretical generated energy of the wind turbine generator with higher precision.
Description
Technical Field
The invention belongs to the field of wind power control, and particularly relates to a wind power plant theoretical generated energy calculation method based on real-time power remote measurement.
Background
At present, the statistical method of the theoretical generated energy of the wind turbine generator is mainly a plate sampling method and a power curve extrapolation method. Through sampling analysis, the monthly statistical error of the plate sampling method is about 8%, the monthly statistical error of the power curve extrapolation method is about 11%, the statistical error is larger, and the statistical error is larger for the two methods in the mountain wind field. In addition, when the sample board machine has communication faults and can not obtain the power data of the sample board machine, the power generation amount statistics is forced to be interrupted.
Therefore, the method for calculating the theoretical power generation amount of the wind power plant with high precision and good robustness is researched.
Disclosure of Invention
The invention has the technical problems that the existing sample board method and the power curve extrapolation method have larger statistical error on the theoretical generated energy of the wind turbine generator and cause the interruption of the generated energy statistics when communication faults occur and power data cannot be read in real time.
The invention aims to solve the problems and provides a wind power plant theoretical generated energy calculation method based on real-time power remote measurement, which comprises the steps of obtaining real-time active power remote measurement of a wind turbine generator, calculating and predicting power errors of a sample computer method and a power curve extrapolation method, predicting the power errors of the sample computer method and the power curve extrapolation method by using an LSTM model, determining weights according to the power errors of the sample computer method and the power curve extrapolation method, carrying out weighted summation on the active power of the sample computer method and the active power of the power curve extrapolation method, obtaining reference power, integrating the reference power serving as the basis of unit theoretical generated energy statistics, obtaining the theoretical generated energy of the wind turbine generator, improving the calculation precision of the theoretical generated energy and increasing the robustness of a statistical method.
The technical scheme of the invention is a wind power plant theoretical generating capacity calculating method based on real-time power remote measurement, an LSTM model is established for each wind power unit, the LSTM model is used for predicting active power errors obtained by a board computer method and a power curve extrapolation method, a power calibration value of the board computer method and a power calibration value of the power curve extrapolation method are obtained, so as to improve the precision of the theoretical generating capacity obtained by the board computer method and the power curve extrapolation method, the wind power plant theoretical generating capacity calculating method comprises the following steps,
step 1: communicating with a controller for measuring the wind turbine at present to obtain the remote measurement of the real-time active power of the wind turbine;
step 2: acquiring real-time active power of a sample board computer, calculating a difference value between the real-time active power of the sample board computer and the measured real-time active power of the wind turbine generator, and calculating to obtain a power error of the sample board computer;
and step 3: calculating to obtain the active power of the wind turbine generator set by adopting a power curve extrapolation method, and comparing the active power with the telemetering measurement of the real-time power of the generator set to calculate to obtain the power error of the power curve extrapolation method;
and 4, step 4: respectively taking the real-time active power error of the sample board machine and the power error of the power curve extrapolation method as the input of an LSTM model, and predicting the power error of the sample board machine and the power error of the power curve extrapolation method;
and 5: determining the weight of the power of the sample board machine and the weight of the power curve extrapolation method according to the power error of the sample board machine and the power error of the power curve extrapolation method, and performing weighted summation on the active power calibration value of the sample board machine and the active power calibration value of the power curve extrapolation method to obtain reference power;
step 6: and integrating the reference power serving as the basis of the theoretical generating capacity statistics of the wind turbine generator set to obtain the theoretical generating capacity of the wind turbine generator set.
And if the sample board machine has communication abnormity, taking the active power obtained by the power curve extrapolation method as the basis of the theoretical generated energy statistics of the wind turbine generator.
And if the wind turbine generator which is used for counting the generated energy at present is abnormal in communication, taking the active power obtained by the sample board machine as the basis of the theoretical generated energy statistics of the wind turbine generator.
Preferably, step 5 employs a genetic algorithm to determine a weight of the power of the template and a weight of the power curve extrapolation.
Compared with the prior art, the invention has the beneficial effects that:
1) the method determines the weight according to the power errors of the sample board machine and the power curve extrapolation method, performs weighted summation on the active power of the sample board machine and the power curve extrapolation method, and takes the obtained reference power as the integral basis of the theoretical generated energy of the wind turbine generator so as to obtain the theoretical generated energy of the wind turbine generator with higher precision;
2) according to the invention, the LSTM model is used for predicting the power errors of the sample board machine and the power curve extrapolation method, so that the influence of the power errors of the sample board machine and the power curve extrapolation method on the theoretical generated energy statistics is reduced conveniently, and the statistical accuracy is further improved;
3) the reasonable weight of the power of the sample board machine and the predicted power of the power curve extrapolation method is calculated and determined by using the genetic algorithm, so that the accuracy of the theoretical generated energy reference power calculated value of the fan is improved;
4) according to the invention, the reference power calculated according to the power of the sample board machine and the power curve extrapolation method is used as the integral basis of the theoretical generating capacity of the unit, so that the transmission quantity of the power data of the unit can be greatly reduced, and the reliability of a communication channel of the unit is improved;
5) according to the invention, when the communication of the sample board computer is abnormal, the theoretical generating capacity of the unit can be calculated, the calculation precision is ensured, and the robustness is good.
Drawings
The invention is further illustrated by the following figures and examples.
Fig. 1 is a schematic flow chart of a method for calculating theoretical power generation of a wind farm according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of calculation of theoretical power generation capacity of a wind farm according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of the cell structure of the LSTM model according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1 and 2, the method for calculating theoretical generated energy of a wind farm based on real-time power remote measurement establishes an LSTM model for each wind turbine, and predicts the error of active power obtained by a board sampling method and a power curve extrapolation method by using the LSTM model as shown in fig. 3, so as to improve the precision of theoretical generated energy obtained by the board sampling method and the power curve extrapolation method, the method for calculating theoretical generated energy of the wind farm comprises the following steps,
step 1: communicating with a controller for measuring the wind turbine at present to obtain the telemetering amount Pr of the real-time active power of the wind turbine;
step 2: real-time active power P of sample board machine1And calculating the difference value between the real-time active power of the sample board machine and the measured real-time active power of the wind turbine generator set to obtain the power error e of the sample board machine1;
And step 3: calculating to obtain active power P of the wind turbine generator system by adopting a power curve extrapolation method2Comparing with the remote measurement of the real-time power of the unit, calculating to obtain the power error e of the power curve extrapolation method2;
And 4, step 4: respectively taking the real-time active power error of the sample board machine and the power error of the power curve extrapolation method as the input of an LSTM model, predicting the power error of the sample board machine and the power error of the power curve extrapolation method to obtain a predicted sample board machine power error E1Power error E of extrapolation of sum power curve2;
And 5: determining the weight epsilon of the power of the sample board machine by adopting a particle swarm algorithm according to the power error of the sample board machine and the power error of a power curve extrapolation method1Weight of power of extrapolation of power curve ε2=1-ε1Calibration value P for active power of sample board machine1-E1Active power calibration value P of sum power curve extrapolation method2-E2Carrying out weighted summation to obtain reference power,
P=ε1(P1-E1)+ε2(P2-E2) (1)
step 6: and integrating the reference power serving as the basis of the theoretical generating capacity statistics of the wind turbine generator set to obtain the theoretical generating capacity of the wind turbine generator set.
If the sample board machine is abnormal in communication, taking active power obtained by power curve extrapolation as the basis of theoretical generated energy statistics of the wind turbine generator, and taking reference power P as P2-E2。
If the wind turbine generator which is used for counting the generated energy at present is abnormal in communication, the active power obtained by the sample board machine is used as the basis of the theoretical generated energy counting of the wind turbine generator, and the reference power P is P1-E1。
In the embodiment, the telemetering amount Pr of the real-time active power of the unit is taken once every 5 minutes, and power data points formed according to the time sequence are used as sample points of a power curve extrapolation method.
The power curve extrapolation method adopts exponential smoothing to obtain the power per minute from t +60S to t +300S, wherein t is the current moment. The power curve extrapolation method of the embodiment refers to an exponential curve trend extrapolation method disclosed by 'Beijing power load medium and long term prediction based on a measurement economics model' paper of Yan celebration friend published in 7 months & lthydroelectric energy science & gt, 2013.
Respectively calculating the telemetering amount Pr of the real-time active power of the unit obtained at the current moment t and the power error e of the sample board machine1And power error e extrapolated from the power curve2As an input of the LSTM model, the LSTM model has a power error E for the sample plate machine per minute for a time period from t +60S to t +300S1And power error E of the power curve extrapolation2Predicting, and respectively combining with the active power of the sample board computer at the corresponding moment and the active power calculated by the power curve extrapolation method to respectively obtain the active power calibration value P of the sample board computer1-E1And the active power calibration value P of the power curve extrapolation method2-E2And (2) carrying out weighted summation by adopting the formula (1) to obtain reference power P, and integrating the reference power P to obtain the theoretical generating capacity of the unit.
Determining the weight epsilon of the power of a sample board machine by adopting a particle swarm algorithm1The specific process is as follows:
1) initializing a group of particles, including their random positions and velocities, to be dispersed throughout space; the position of the ith particle represents the ith weight parameter xiThe position change speed of the ith particle is viThe number of the particles ranges from 20 to 30;
2) x is to beiAs a weight of the power of the template machine, 1-xiCalculating the mean square error of the reference power P and the measured power sample of the unit as the weight of the power curve extrapolation method, and taking the reciprocal of the mean square error as the fitness value of the particles, wherein the smaller the mean square error is, the better the fitness of the particles is;
3) comparing the fitness value of each particle with the fitness value of the historical optimal position of the particle, and recording the historical optimal position of the ith particle as gbiIf the current fitness value ratio gbiIf the fitness value is good, the particle position corresponding to the fitness value is taken as the current best position gbiOn the contrary, gbiKeeping the same;
4) sorting according to the fitness, hybridizing the particles, calculating the positions and the speeds of the child particles, comparing the fitness of the child particles with the fitness of the parent particles, and replacing the speeds and the positions of the parent particles with the speeds and the positions of the child particles if the fitness of the child is better than that of the parent particles; calculating the velocity and position of the daughter particle according to equations (2) and (3):
vc=(v1+v2)*|v1|/|v1+v2| (2)
xc=rand()*x1+(1-rand())*x2 (3)
in the formula vcIs the daughter particle velocity, xcIs the daughter particle position, v1、v2For the speed of the selected particles to be hybridized, x1、x2Rand () is a random number in the interval (0, 1) for the position of the selected particle to be hybridized;
5) selecting particles for variation, calculating the positions of the variation particles, comparing the adaptability of the variation particles with the adaptability of the original particles, and replacing the positions of the original particles with the variation particles if the adaptability of the variation particles is better than that of the original particles; calculating the position of the variant particle according to equation (4):
xm=x3*(1+rand()) (4)
wherein x3To select the position of the particle to be varied, xmPosition of the altered particle, rand ()Is a random number in the interval (0, 1);
6) calculating the fitness of the particles after hybridization variation, and recording the optimal positions found by all the particles as Zb which is GbiThe best value is the global optimal position of the whole population in one iteration, and the fitness value of each particle is compared with the fitness values of the optimal positions Zb found by all the particles; if the current fitness value is better than Zb, taking the position as the global optimal position Zb of all the particles, otherwise, keeping Zb unchanged;
7) updating the speed and the position of the particles according to the formula (5) and the formula (6);
vi(new)=w×vi(old)+c1×rand()×(gbi-xi(old))+c2×rand()×(Zb-xi(old)) (5)
xi(new)=xi(old)+μ×vi(new) (6)
in the formula vi(old) represents the particle velocity at the previous time, vi(new) denotes the new time particle velocity, xi(old) represents the position of the particle at the previous time, xi(new) denotes the new time particle position, gbiRepresents the optimal position of the ith particle, Zb represents the global optimal position of the particle group, w represents the inertial right, c1、c2All are learning factors, mu is a constraint factor.
8) Judging whether the maximum iteration times is reached, if the maximum iteration times is reached, ending the process, and taking the obtained Zb as the weight epsilon1(ii) a Otherwise, step 2) is executed.
Given a current input xtLast moment implies layer state ht-1And storage state Ct-1Input gate of LSTM itForgetting door ftAnd an output gate otCandidate memory cellNew memory state CtHidden layer state htCurrent iteration value it,i、ft,i、ot,i、Ct,i、ht,iThe calculation process is as follows:
it=σ(Wi[xt,ht-1]T+bi)
ft=σ(Wf[xt,ht-1]T+bf)
ot=σ(Wo[xt,ht-1]T+bo)
ht=ot⊙tanh(Ct)
wherein Wi、Wf、Wo、WcRespectively represent corresponding weight matrices, bi、bf、bo、bcRespectively represent corresponding offset vectors; σ (-) and tanh (-) are Sigmoid and tangent Sigmoid curve activation functions, respectively; final output of the output layerBy hidden layer states htAnd (3) calculating:
wherein WSIs the connection weight matrix of the hidden layer and the output layer, bSRepresenting the corresponding offset vector.
The implementation result shows that the theoretical generating capacity of a single wind turbine generator is obtained through statistics by the wind power plant theoretical generating capacity calculation method based on real-time power remote measurement, the monthly statistical error is about 5%, the statistical accuracy is improved compared with a sample computer and a power curve extrapolation method, the remote measurement of the real-time active power of the wind turbine generator is not required to be read every minute, and the statistics of the theoretical generating capacity of the current wind turbine generator is not influenced when the sample computer or the current statistical wind turbine generator is occasionally abnormal in communication and the power data of the sample computer or the real-time active power remote measurement cannot be read.
Claims (3)
1. A method for calculating theoretical generated energy of a wind power plant based on real-time power remote measurement is characterized in that an LSTM model is established for each wind power plant, errors of active power obtained by a board computer method and a power curve extrapolation method are predicted by utilizing the LSTM model, a power calibration value of the board computer method and a power calibration value of the power curve extrapolation method are obtained, so that the precision of the theoretical generated energy obtained by the board computer method and the power curve extrapolation method is improved, and the method for calculating the theoretical generated energy of the wind power plant comprises the following steps,
step 1: communicating with a controller for measuring the wind turbine at present to obtain the remote measurement of the real-time active power of the wind turbine;
step 2: acquiring real-time active power of a sample board machine, and calculating a difference value between the real-time active power of the sample board machine and the measured real-time active power of the wind turbine generator to obtain a power error of the sample board machine;
and step 3: calculating to obtain the active power of the wind turbine generator by adopting a power curve extrapolation method, and comparing the active power with the telemetering amount of the real-time power of the wind turbine generator to calculate to obtain the power error of the power curve extrapolation method;
and 4, step 4: respectively taking the real-time active power error of the sample board machine and the power error of the power curve extrapolation method as the input of an LSTM model, and predicting the power error of the sample board machine and the power error of the power curve extrapolation method;
and 5: determining the weight epsilon of the power of the sample board machine by adopting a particle swarm algorithm according to the power error of the sample board machine and the power error of a power curve extrapolation method1Weight of power of extrapolation of power curve ε2=1-ε1Calibration value P for active power of sample board machine1-E1By extrapolation of the sum power curveActive power calibration value P2-E2Carrying out weighted summation to obtain reference power,
P=ε1(P1-E1)+ε2(P2-E2) (1)
P1representing real-time active power of the board computer, E1Indicating predicted power error of the template machine, P2Calculating to obtain the active power of the wind turbine generator by representing the power curve by an extrapolation method, E2A power error representing an extrapolation of the power curve;
step 6: and integrating the reference power serving as the basis of the theoretical generating capacity statistics of the wind turbine generator set to obtain the theoretical generating capacity of the wind turbine generator set.
2. The method for calculating the theoretical generated energy of the wind power plant based on the real-time power remote measurement is characterized in that if the communication of the sample board computer is abnormal, the active power obtained by the power curve extrapolation method is used as the basis of the theoretical generated energy statistics of the wind power unit.
3. The method for calculating the theoretical generated energy of the wind power plant based on the real-time power remote measurement is characterized in that if the communication of the wind power plant for calculating the generated energy is abnormal at present, the active power obtained by the sample board machine is used as the basis for calculating the theoretical generated energy of the wind power plant.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110083075.0A CN112784215B (en) | 2021-01-21 | 2021-01-21 | Wind power plant theoretical generating capacity calculation method based on real-time power remote measurement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110083075.0A CN112784215B (en) | 2021-01-21 | 2021-01-21 | Wind power plant theoretical generating capacity calculation method based on real-time power remote measurement |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112784215A CN112784215A (en) | 2021-05-11 |
CN112784215B true CN112784215B (en) | 2022-04-15 |
Family
ID=75758257
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110083075.0A Active CN112784215B (en) | 2021-01-21 | 2021-01-21 | Wind power plant theoretical generating capacity calculation method based on real-time power remote measurement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112784215B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107330183A (en) * | 2017-06-29 | 2017-11-07 | 华北电力大学 | A kind of wind power utilization computational methods based on service data |
CN108388962A (en) * | 2018-02-06 | 2018-08-10 | 北京天润新能投资有限公司 | A kind of wind power forecasting system and method |
CN109034607A (en) * | 2018-07-24 | 2018-12-18 | 南方电网科学研究院有限责任公司 | Optical quantum appraisal procedure, system, device and readable storage medium storing program for executing are abandoned in abandonment |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101425016B1 (en) * | 2012-09-18 | 2014-08-01 | 한국전력공사 | Method for Automatically Generating Power Curve Limits for Power Curve Monitoring in Wind Turbines |
CN104123456A (en) * | 2014-07-21 | 2014-10-29 | 北京中科伏瑞电气技术有限公司 | Classified statistic method and system of wind curtailment electric quality of wind power plant |
CN107194625B (en) * | 2017-07-25 | 2020-11-24 | 国家电网公司 | Wind power plant wind curtailment electric quantity evaluation method based on neural network |
-
2021
- 2021-01-21 CN CN202110083075.0A patent/CN112784215B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107330183A (en) * | 2017-06-29 | 2017-11-07 | 华北电力大学 | A kind of wind power utilization computational methods based on service data |
CN108388962A (en) * | 2018-02-06 | 2018-08-10 | 北京天润新能投资有限公司 | A kind of wind power forecasting system and method |
CN109034607A (en) * | 2018-07-24 | 2018-12-18 | 南方电网科学研究院有限责任公司 | Optical quantum appraisal procedure, system, device and readable storage medium storing program for executing are abandoned in abandonment |
Non-Patent Citations (1)
Title |
---|
风电场理论功率计算方法的分析与讨论;李国庆等;《新疆电力技术》;20170915(第03期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112784215A (en) | 2021-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110705743B (en) | New energy consumption electric quantity prediction method based on long-term and short-term memory neural network | |
CN109670629B (en) | Coal-fired boiler thermal efficiency prediction method based on long-short term memory neural network | |
CN103023065B (en) | Wind power short-term power prediction method based on relative error entropy evaluation method | |
CN110807554A (en) | Generation method and system based on wind power/photovoltaic classical scene set | |
CN108428017B (en) | Wind power interval prediction method based on nuclear extreme learning machine quantile regression | |
CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
CN112001113B (en) | Battery life prediction method based on particle swarm optimization long-time and short-time memory network | |
CN112818604A (en) | Wind turbine generator risk degree assessment method based on wind power prediction | |
CN110796281B (en) | Wind turbine state parameter prediction method based on improved deep belief network | |
CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
CN115186555B (en) | Digital twinning-based drying equipment live simulation method and related equipment | |
CN113705922A (en) | Improved ultra-short-term wind power prediction algorithm and model establishment method | |
CN115759415A (en) | Power consumption demand prediction method based on LSTM-SVR | |
CN116451556A (en) | Construction method of concrete dam deformation observed quantity statistical model | |
CN116930609A (en) | Electric energy metering error analysis method based on ResNet-LSTM model | |
CN112001537A (en) | Short-term wind power prediction method based on gray model and support vector machine | |
CN116757057A (en) | Air quality prediction method based on PSO-GA-LSTM model | |
CN112784215B (en) | Wind power plant theoretical generating capacity calculation method based on real-time power remote measurement | |
CN116774086B (en) | Lithium battery health state estimation method based on multi-sensor data fusion | |
CN114487890A (en) | Lithium battery health state estimation method for improving long-term and short-term memory neural network | |
CN113627594A (en) | One-dimensional time sequence data amplification method based on WGAN | |
CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
CN113159395A (en) | Deep learning-based sewage treatment plant water inflow prediction method and system | |
CN111753466A (en) | Soft measurement modeling method for radial displacement of rotor of three-pole magnetic bearing | |
CN114859231B (en) | Battery remaining life prediction method based on wiener process and extreme learning machine |
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 | ||
GR01 | Patent grant |