CN106447134A - Classified short-term power forecast method for small hydropower stations - Google Patents
Classified short-term power forecast method for small hydropower stations Download PDFInfo
- Publication number
- CN106447134A CN106447134A CN201610962307.9A CN201610962307A CN106447134A CN 106447134 A CN106447134 A CN 106447134A CN 201610962307 A CN201610962307 A CN 201610962307A CN 106447134 A CN106447134 A CN 106447134A
- Authority
- CN
- China
- Prior art keywords
- radial
- flow type
- power station
- type small
- small 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 55
- 238000012706 support-vector machine Methods 0.000 claims description 18
- 238000011144 upstream manufacturing Methods 0.000 claims description 12
- 238000000205 computational method Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000009931 harmful effect Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000001105 regulatory 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a classified short-term power forecast method for small hydropower stations. The classified short-term power forecast method includes collecting data information of regional runoff-type small hydropower stations and regional non-runoff-type small hydropower stations; forecasting the short-term power of the regional runoff-type small hydropower stations through runoff-type small hydropower station direction forecast and BP neural network forecast, calculating weight coefficients of forecast values of the two methods according to the entropy weight method, and calculating short-term power forecast values of the regional runoff-type small hydropower stations at the j moment; calculating short-term power forecast values of the regional non-runoff-type small hydropower stations at the j moment; acquiring short-term power forecast values of regional small hydropower stations according to the short-term power forecast values of the regional runoff-type small hydropower stations at the j moment and the short-term power forecast values of the regional non-runoff-type small hydropower stations at the j moment. By the classified short-term power forecast method, the technical problems, such as low forecast accuracy and large forecast error in short-term power forecast of the small hydropower stations in the prior art, caused due to the fact that the influence factors of the small hydropower stations are different and data sources and data sizes are highly different when the short-term power forecast of the small hydropower stations is performed according to the prior art are solved.
Description
Technical field
The short term power prediction side the invention belongs to small power station's short term power Predicting Technique, more particularly to a kind of small power station are classified
Method.
Background technology
Increasingly serious with environmental pollution and energy shortage problem, small power station is used as the renewable replacement energy of cleaning green
Source, different from big-and-middle-sized water power, is mainly distributed on the mountain area of remote geographic location, is the important power supply composition portion in rural area
Point, with sporadic development, become on the spot net, on the spot power supply, build and that cost of electricity-generating is low, the construction period is short, return income is fast etc. is excellent
Point, therefore quickly grows under the support of country and local policy with irreplaceable advantage, solves well partly
The short of electricity situation in area.
At the same time, the development of small power station also brings some problems, and small power station is divided into radial-flow type small power station and non-radial-flow type
Small power station.At present great majority are run-of-river small hydropower station, its no storage capacity regulating power substantially, with strong seasonality, flood season water
More, in full hair-like state more than small power station, withered phase water is less, and small power station's generated energy is substantially reduced, and its generation load performance is very strong
Uncertainty.Small hydropower station changes of operating modes is larger, and (non-radial-flow type water power includes non-footpath by the non-radial-flow type water power in upstream
The big water power of streaming and non-radial-flow type small power station) affect larger, Unit Commitment is frequent, causes the fluctuation of major network trend big, increases circuit
The out-of-limit probability of trend.Rather than run-of-river small hydropower station, although its proportion in systems is less, and reservoir has necessarily
Regulation performance, can participate in regional load peak regulation work, but its adjust poor-performing, the wet season small power station City Regions with
The increase of discharge, is easily clashed with big-and-middle-sized water power, electrical network major network is impacted, if sending out for small power station is not grasped in scheduling
Electrical information, the harmful effect brought by power network safety operation and dispatching of power netwoks etc. will be notable all the more.Accordingly, it would be desirable to right
Small power station carries out short term power prediction.But as radial-flow type small power station and non-radial-flow type small power station are in the method for operation by being affected
Factor difference, and as the difference of the aspects such as way to manage causes the difference of the source data amount of data big, existing little water
Electric Forecasting Methodology does not all consider the problem of the above, if single enters according to radial-flow type small power station or non-radial-flow type small power station
Row prediction, will all cause prior art small power station short term power precision of prediction is low, and forecast error is big etc..
Content of the invention:
The technical problem to be solved in the present invention:A kind of small power station classification short term power Forecasting Methodology is provided, small power station is divided
It is that radial-flow type small power station and the classification of non-radial-flow type small power station carry out short term power prediction, to solve existing small power station's Forecasting Methodology
All do not consider that radial-flow type small power station is different with the influence factor that non-radial-flow type small power station is subject in the method for operation, and due to manager
The difference such as formula causes the difference of the source data amount of data greatly, and single little according to radial-flow type small power station or non-radial-flow type
Water power is predicted causing that prior art small power station short term power precision of prediction is low, the technical problem such as forecast error is big.
Technical solution of the present invention:
A kind of small power station's classification short term power Forecasting Methodology, it is characterised in that:It includes
The data message of step 1, the regional radial-flow type small power station of collection and non-radial-flow type water power;
Step 2, by radial-flow type small power station directly prediction and BP neural network prediction to carry out radial-flow type small power station respectively short
Phase power prediction, and the weight coefficient of two methods predictive value is asked for using entropy assessment, calculate regional radial-flow type small power station jth
Moment short term power predictive value Prj;
Step 3, the regional non-radial-flow type small power station jth moment short term power predictive value P of calculatingnrj;
Step 4, according to regional radial-flow type small power station jth moment short term power predictive value PrjWith regional non-radial-flow type small power station
Jth moment short term power predictive value Pnrj, obtain regional small power station's short term power predictive value Pj=Prj+Pnrj.
Collection area radial-flow type small power station data message described in step 1 includes meteorological data, goes out force data, startup-shutdown number
According to the meteorological data should be including the temperature of radial-flow type small power station region, air pressure, humidity, wind direction, wind speed, rainfall number
According to;The data message of the non-radial-flow type water power includes meteorological data, goes out force data, the outbound water yield, startup-shutdown data, meteorological number
Little according to temperature, air pressure, humidity, wind direction, wind speed, rainfall product data and the non-radial-flow type that should include non-radial-flow type water power region
The time-of-use tariffs data of the Medium and long term generation scheduling of water power and area power grid.The regional radial-flow type small power station jth moment described in step 2
Short term power predictive value PrjComputational methods include:
Step 2.1, discharge Q in i-th radial-flow type small power station jth moment of calculatingrij=Qr1ij+Qr2ij, in formula:Qr1ijFor
The rainfall of radial-flow type small power station region;Qr2ijThe outbound water yield for the non-radial-flow type water power in upstream;
Step 2.2, i-th radial-flow type small power station the first short term power of jth moment predictive value P of calculatingr1ij,
Pr1ij=ki·Qrij·HiIn formula:Pr1ijFor i-th radial-flow type small power station the first short term power of jth moment predictive value
Pr1ij, unit is W;QrijFor the discharge in i-th radial-flow type small power station jth moment, unit is m3/s;HiFor i-th radial-flow type
The average water head of small power station, unit is m;kiPower factor for i-th radial-flow type small power station;
Calculate the first short term power predictive value P in regional radial-flow type small power station jth momentr1j;
In formula:N is the total quantity of regional radial-flow type small power station;
Step 2.3, according to i-th radial-flow type small power station meteorological data, go out force data, carry out BP neural network prediction, obtain
The second short term power predictive value P to the regional radial-flow type small power station jth momentr2j;
Step 2.4, determine Pr1jAnd Pr2jWeight coefficient wr1、wr2, and prediction jth moment day is calculated, regional radial-flow type is little
Water
Electric short term power predictive value Prj,
Step 2.5, calculating predict that the history of ξ r days a few days ago goes out the error ε of force data and prediction datarIf, continuous ξ r days
Error εrRadial-flow type small power station short term power precision of prediction threshold value er for setting is all higher than, re-starts step 2.5;Less than then defeated
Go out to predict jth moment day area radial-flow type small power station short term power predictive value Prj.
The method bag of the second short term power predictive value Pr2j in the regional radial-flow type small power station jth moment described in step 2.3
Include:
Step 2.3.1, three layers of BP neural network are used, the input vector of given BP neural network power prediction model goes forward side by side
Row normalized;The input layer number of the BP neural network power prediction model is 7, according to institute of radial-flow type small power station
Temperature Tr in the meteorological data in region, air pressure Pr, humidity Hr, wind direction Wdr, wind speed Wsr, rainfall Qr1, the non-runoff in upstream
Formula water power outbound water yield Qr2, forms the input vector Y of BP neural network power prediction modelr=[Tr, Pr, Hr, Wdr, Wsr,
Qr1、Qr2];Described its formula is normalized to input vector Yr it is
Y' in formularijFor jth moment, the normalization of i-th radial-flow type small power station
Input vector after process;YrijFor jth moment, the input vector before i-th radial-flow type small power station normalized;max(Yri)
With min (Yri) represent maximum and the minima of i-th radial-flow type small power station input vector respectively;
Step 2.3.2, selection prediction δ r day data a few days ago are trained to BP neural network, obtain as training sample
BP neural network power prediction model after must training;
Step 2.3.3, will prediction jth moment day, temperature Tr of i-th radial-flow type small power station regionij, air pressure
Prij, humidity Hrij, wind direction Wdrij, wind speed Wsrij, rainfall Qr1ijOutbound water yield Q with the non-radial-flow type water power in upstreamr2ijAs
Input layer, is input in the BP neural network power prediction model after training, and output layer data is prediction jth moment day, i-th
Radial-flow type small power station the second short term power predictive value pr2ij;
Step 2.3.4, the second short term power predictive value P in calculating regional radial-flow type small power station jth momentr2j
P in formular2ijFor predicting jth moment day, i-th the second short-term of radial-flow type small power station
Power prediction value, n is the total quantity of regional radial-flow type small power station.
Regional radial-flow type small power station short term power predictive value P described in step 2.4 and step 2.5rjComputational methods include
Step 2.4.1 is according to prediction θ a few days agorIt history meteorological data and history go out force data, calculate first respectively short
Phase power prediction value Pr1(1)j...Pr1(θr)jWith the second short term power predictive value Pr2(1)j...Pr2j(θr)j, and count actual power value
For Pr1...Prθr;
Step 2.4.2, respectively with the first short term power predictive value and the second short term power predictive value and actual power value
Error Absolute Value is evaluation index, determines weight coefficient w with entropy assessmentr1And wr2;wr1For Pr1jWeight coefficient, wr2For Pr2j's
Weight coefficient;wr1+wr2=1;
Step 2.4.3, pass through formula Prj=wr1×Pr1j+wr2×Pr2jCalculate prediction jth moment day, regional radial-flow type
Small power station short term power predictive value Prj;
Step 2.4.4, calculating predict that the history of ξ r days a few days ago goes out the error ε r of force data and prediction data, if continuous ξ r
Its error ε r is all higher than radial-flow type small power station short term power precision of prediction threshold value er for setting, and re-starts step 2.4.3;It is less than
Then jth moment day is predicted in output, regional radial-flow type small power station short term power predictive value Prj.
The non-radial-flow type small power station jth moment short term power predictive value P in calculating area described in step 3nrjMethod include under
State step:
When step 3.1, the historical data according to k-th non-radial-flow type small power station of jth moment and meteorological data calculate jth
Carve, k-th non-the first short term power of radial-flow type small power station predictive value Pnr1kj;Pnr1kj=kk·Qnrkj·HkjIn formula:kkFor k-th
The power factor of non-radial-flow type small power station, HkjHead for k-th non-radial-flow type small power station of jth moment;QnrkjFor the jth moment
The discharge of k Ge Fei radial-flow type small power station;
Step 3.2, jth moment the first short term power predictive value P of the regional non-radial-flow type small power station of calculatingnr1j;In formula:M is the quantity of regional non-radial-flow type small power station;
Step 3.3, in the jth moment, historical data according to the non-radial-flow type small power station of k-th radial-flow type, meteorological data and
The time-of-use tariffs of area power grid, are calculated the second short term power prediction of regional non-radial-flow type small power station using support vector machine
Value Pnr2j;
Step 3.4, determine Pnr1jAnd Pnr2jWeight coefficient wnr1、wnr2, calculate the non-radial-flow type in prediction jth moment day area
Small power station short term power predictive value Pnrj;
ξ a few days ago is predicted in step 3.5, calculatingnrIt history goes out the error ε of force data and prediction datanrIf, continuous ξnr
Its error εnrIt is all higher than non-radial-flow type small power station short term power precision of prediction threshold value e for settingnr, then re-start step 3.4;
It is less than or equal to and then exports non-radial-flow type small power station short term power predictive value Pnrj.
Second short term power predictive value P of the non-radial-flow type small power station in area described in step 3.3nr2jComputational methods, its
Step includes:
Step 3.3.1, the input vector of given support vector machine power prediction model are simultaneously normalized;According to non-
The meteorological data of radial-flow type small power station region:Temperature Tnr, air pressure Pnr, humidity Hnr, wind direction Wdnr, wind speed WnrsAnd rainfall
Qnr1, area power grid time-of-use tariffs Cnr, formed support vector machine power prediction model input vector Ynr:
Ynr=[Tnr、Pnr、Hnr、Wdnr、Wsnr、Qnr1、Cnr];
Input vector Ynr is normalized, and its formula is:
In formula:Y'nrkjFor jth moment, the normalization of k-th non-radial-flow type small power station
Input vector after process;YnrkjFor jth moment, the input vector before k-th non-radial-flow type small power station normalized;max
(Ynrk) and min (Ynrk) represent the maximum of k-th non-radial-flow type small power station variable and minima respectively;
δ a few days ago is predicted in step 3.3.2, selectionnrIts YnrkjData are instructed using support vector machine as training sample
Practice, obtain the support vector machine power prediction model after training;
Step 3.3.3, will prediction jth moment day, temperature T of k-th non-radial-flow type small power station regionnrkj, air pressure
Pnrkj, humidity Hnrkj, wind direction Wdnrkj, wind speed Wsnrkj, rainfall Qnr1kjTime-of-use tariffs C with area power gridnrkjAs input
Layer, is input in the support vector machine power prediction model after training, and output layer data is prediction jth moment day, k-th non-footpath
Streaming small power station short term power predictive value pnr2kj;
Step 3.3.4, regional non-radial-flow type small power station jth moment the second short term power predictive value P of calculatingnr2j, its formula
For:
P described in step 3.4nr1jAnd Pnr2jWeight coefficient wnr1、wnr2Determination method include:
θ a few days ago is predicted in step 3.4.1, acquisitionnrIt history meteorological data and history go out force data;
Step 3.4.2, calculate respectively regional non-radial-flow type small power station first prediction performance number Pnr1(1)j...Pnr1(θnr)j
With the second power prediction value Pnr2(1)j...Pnr2j(θnr)j;
Step 3.4.3, acquisition actual power value are Pnr1...Pnrθnr;
Step 3.4.4, with predict performance number and actual power value Error Absolute Value as evaluation index, determined with entropy assessment
Weight coefficient wnr1、wnr2, wnr1+wnr2=1.
Calculate the non-radial-flow type small power station short term power predictive value P in prediction jth moment day areanrjFormula be:
Pnrj=wnr1×Pnr1j+wnr2×Pnr2j.
Beneficial effects of the present invention:
The present invention provides a kind of small power station and classifies short term power Forecasting Methodology, and small power station is divided into radial-flow type small power station and non-
Radial-flow type small power station carries out classification prediction, and radial-flow type small power station and non-radial-flow type small power station are utilized respectively combination forecasting method and enter
Row short term power is predicted, to make up the prediction defect of single method, while ask for the power of two methods predictive value using entropy assessment
Weight coefficient, and track continuous operation forecast error in a few days and in time weight coefficient is modified, to efficiently reduce prediction by mistake
Difference, raising precision of prediction.Solve existing small power station's Forecasting Methodology and all do not consider radial-flow type small power station and the little water of non-radial-flow type
Influence factor's difference that electricity is subject in the method for operation, and as the difference such as way to manage causes the difference of the source data amount of data
Different big, and single be predicted causing prior art small power station short-term according to radial-flow type small power station or non-radial-flow type small power station
Power prediction precision is low, the technical problem such as forecast error is big.
Specific embodiment
A kind of small power station's classification short term power Forecasting Methodology, it includes:
The data message of step 1, the regional radial-flow type small power station of collection and non-radial-flow type water power;
Collection area radial-flow type small power station data message described in step 1 includes meteorological data, goes out force data, startup-shutdown number
According to the meteorological data should be including the temperature of radial-flow type small power station region, air pressure, humidity, wind direction, wind speed, rainfall number
According to;The data message of the non-radial-flow type water power includes meteorological data, goes out force data, the outbound water yield, startup-shutdown data, meteorological number
Little according to temperature, air pressure, humidity, wind direction, wind speed, rainfall product data and the non-radial-flow type that should include non-radial-flow type water power region
The time-of-use tariffs data of the Medium and long term generation scheduling of water power and area power grid.
Geographic position data should include affiliated basin situation and the geographical position of non-radial-flow type water power and radial-flow type small power station
Put.
Step 2, by radial-flow type small power station directly prediction and BP neural network prediction to carry out radial-flow type small power station respectively short
Phase power prediction, and the weight coefficient of two methods predictive value is asked for using entropy assessment, calculate regional radial-flow type small power station jth
Moment short term power predictive value Prj;
Area radial-flow type small power station jth moment short term power predictive value P described in step 2rjComputational methods include:
Step 2.1, in the jth moment, by the startup-shutdown feelings of the non-radial-flow type water power of i-th radial-flow type small power station and its upstream
The rainfall Q of radial-flow type small power station region in condition, meteorological datar1ijOutbound water yield Q with the non-radial-flow type water power in upstreamr2ij,
Obtain discharge Q of i-th radial-flow type small power stationrij, calculate discharge Q in i-th radial-flow type small power station jth momentrij=
Qr1ij+Qr2ij, in formula:Qr1ijRainfall for radial-flow type small power station region;Qr2ijOutbound for the non-radial-flow type water power in upstream
The water yield;
Step 2.2, i-th radial-flow type small power station the first short term power of jth moment predictive value P of calculatingr1ij,
Pr1ij=ki·Qrij·HiIn formula:Pr1ijFor i-th radial-flow type small power station the first short term power of jth moment predictive value
Pr1ij, unit is W;QrijFor the discharge in i-th radial-flow type small power station jth moment, unit is m3/s;HiFor i-th radial-flow type
The average water head of small power station, unit is m;kiPower factor for i-th radial-flow type small power station;
Calculate the first short term power predictive value P in regional radial-flow type small power station jth momentr1j;
In formula:N is the total quantity of regional radial-flow type small power station;
Step 2.3, according to i-th radial-flow type small power station meteorological data, go out force data, carry out BP neural network prediction, obtain
The second short term power predictive value P to the regional radial-flow type small power station jth momentr2j;
Step 2.3.1, three layers of BP neural network are used, the input vector of given BP neural network power prediction model goes forward side by side
Row normalized;The input layer number of BP neural network power prediction model is 7, according to radial-flow type small power station location
Temperature Tr in the meteorological data in domain, air pressure Pr, humidity Hr, wind direction Wdr, wind speed Wsr, rainfall Qr1, the non-radial-flow type water in upstream
Electric outbound water yield Qr2, forms the input vector Y of BP neural network power prediction modelr=[Tr, Pr, Hr, Wdr, Wsr, Qr1,
Qr2];Described its formula is normalized to input vector Yr it is
Y' in formularijFor jth moment, the normalization of i-th radial-flow type small power station
Input vector after process;YrijFor jth moment, the input vector before i-th radial-flow type small power station normalized;max(Yri)
With min (Yri) represent maximum and the minima of i-th radial-flow type small power station input vector respectively;
Method of the node in hidden layer using empirical equation with hands-on determines, output layer nodes are input layer data
The radial-flow type small power station short term power predictive value in corresponding moment
Step 2.3.2, selection prediction δ r day data a few days ago are trained to BP neural network, obtain as training sample
BP neural network power prediction model after must training;Wherein, δ r is bigger, represents the nerve net that historical data is more, after training
The network precision that predicts the outcome is higher.
Step 2.3.3, will prediction jth moment day, temperature Tr of i-th radial-flow type small power station regionij, air pressure
Prij, humidity Hrij, wind direction Wdrij, wind speed Wsrij, rainfall Qr1ijOutbound water yield Q with the non-radial-flow type water power in upstreamr2ijAs
Input layer, is input in the BP neural network power prediction model after training, and output layer data is prediction jth moment day, i-th
Radial-flow type small power station the second short term power predictive value pr2ij;
Step 2.3.4, the second short term power predictive value P in calculating regional radial-flow type small power station jth momentr2j
P in formular2ijFor predicting jth moment day, i-th the second short-term of radial-flow type small power station
Power prediction value, n is the total quantity of regional radial-flow type small power station.
Step 2.4, determine Pr1jAnd Pr2jWeight coefficient wr1、wr2, and prediction jth moment day is calculated, regional radial-flow type is little
Water power short term power predictive value Prj,
Step 2.5, calculating predict that the history of ξ r days a few days ago goes out the error ε of force data and prediction datarIf, continuous ξ r days
Error εrRadial-flow type small power station short term power precision of prediction threshold value er for setting is all higher than, re-starts step 2.5;Less than then defeated
Go out to predict jth moment day area radial-flow type small power station short term power predictive value Prj.
Regional radial-flow type small power station short term power predictive value P described in step 2.4 and step 2.5rjComputational methods include
Step 2.4.1 is according to prediction θ a few days agorIt history meteorological data and history go out force data, calculate first respectively short
Phase power prediction value Pr1(1)j...Pr1(θr)jWith the second short term power predictive value Pr2(1)j...Pr2j(θr)j, and count actual power value
For Pr1...Prθr;
Step 2.4.2, respectively with the first short term power predictive value and the second short term power predictive value and actual power value
Error Absolute Value is evaluation index, determines weight coefficient w with entropy assessmentr1And wr2;wr1For Pr1jWeight coefficient, wr2For Pr2j's
Weight coefficient;wr1+wr2=1;
Step 2.4.3, pass through formula Prj=wr1×Pr1j+wr2×Pr2jCalculate prediction jth moment day, regional radial-flow type
Small power station short term power predictive value Prj;
Step 2.4.4, calculating predict that the history of ξ r days a few days ago goes out the error ε r of force data and prediction data, if continuous ξ r
Its error ε r is all higher than radial-flow type small power station short term power precision of prediction threshold value er for setting, and re-starts step
2.4.3;Less than then output prediction jth moment day, regional radial-flow type small power station short term power predictive value Prj.
Step 3, the regional non-radial-flow type small power station jth moment short term power predictive value P of calculatingnrj;
The non-radial-flow type small power station jth moment short term power predictive value P in calculating area described in step 3nrjMethod include under
State step:
When step 3.1, the historical data according to k-th non-radial-flow type small power station of jth moment and meteorological data calculate jth
Carve, k-th non-the first short term power of radial-flow type small power station predictive value Pnr1kj;Pnr1kj=kk·Qnrkj·HkjIn formula:kkFor k-th
The power factor of non-radial-flow type small power station, HkjHead for k-th non-radial-flow type small power station of jth moment;QnrkjFor the jth moment
The discharge of k Ge Fei radial-flow type small power station;
Step 3.2, jth moment the first short term power predictive value P of the regional non-radial-flow type small power station of calculatingnr1j;In formula:M is the quantity of regional non-radial-flow type small power station;
Step 3.3, in the jth moment, historical data according to the non-radial-flow type small power station of k-th radial-flow type, meteorological data and
The time-of-use tariffs of area power grid, are calculated the second short term power prediction of regional non-radial-flow type small power station using support vector machine
Value Pnr2j;
Second short term power predictive value P of the non-radial-flow type small power station in area described in step 3.3nr2jComputational methods, its
Step includes:
Step 3.3.1, the input vector of given support vector machine power prediction model are simultaneously normalized;According to non-
The meteorological data of radial-flow type small power station region:Temperature Tnr, air pressure Pnr, humidity Hnr, wind direction Wdnr, wind speed WnrsAnd rainfall
Qnr1, area power grid time-of-use tariffs Cnr, formed support vector machine power prediction model input vector Ynr:
Ynr=[Tnr、Pnr、Hnr、Wdnr、Wsnr、Qnr1、Cnr];
Input vector Ynr is normalized, and its formula is:
In formula:Y'nrkjFor jth moment, the normalization of k-th non-radial-flow type small power station
Input vector after process;YnrkjFor jth moment, the input vector before k-th non-radial-flow type small power station normalized;max
(Ynrk) and min (Ynrk) represent the maximum of k-th non-radial-flow type small power station variable and minima respectively;
δ a few days ago is predicted in step 3.3.2, selectionnrIts YnrkjData are instructed using support vector machine as training sample
Practice, obtain the support vector machine power prediction model after training;
Step 3.3.3, will prediction jth moment day, temperature T of k-th non-radial-flow type small power station regionnrkj, air pressure
Pnrkj, humidity Hnrkj, wind direction Wdnrkj, wind speed Wsnrkj, rainfall Qnr1kjTime-of-use tariffs C with area power gridnrkjAs input
Layer, is input in the support vector machine power prediction model after training, and output layer data is prediction jth moment day, k-th non-footpath
Streaming small power station short term power predictive value pnr2kj;
Step 3.3.4, regional non-radial-flow type small power station jth moment the second short term power predictive value P of calculatingnr2j, its formula
For:
Step 3.4, determine Pnr1jAnd Pnr2jWeight coefficient wnr1、wnr2, calculate the non-radial-flow type in prediction jth moment day area
Small power station short term power predictive value Pnrj;
P described in step 3.4nr1jAnd Pnr2jWeight coefficient wnr1、wnr2Determination method include:
θ a few days ago is predicted in step 3.4.1, acquisitionnrIt history meteorological data and history go out force data;
Step 3.4.2, calculate respectively regional non-radial-flow type small power station first prediction performance number Pnr1(1)j...Pnr1(θnr)j
With the second power prediction value Pnr2(1)j...Pnr2j(θnr)j;
Step 3.4.3, acquisition actual power value are Pnr1...Pnrθnr;
Step 3.4.4, with predict performance number and actual power value Error Absolute Value as evaluation index, determined with entropy assessment
Weight coefficient wnr1、wnr2, wnr1+wnr2=1.
Calculate the non-radial-flow type small power station short term power predictive value P in prediction jth moment day areanrjFormula be:
Pnrj=wnr1×Pnr1j+wnr2×Pnr2j.
ξ a few days ago is predicted in step 3.5, calculatingnrIt history goes out the error ε of force data and prediction datanrIf, continuous ξnr
Its error εnrIt is all higher than non-radial-flow type small power station short term power precision of prediction threshold value e for settingnr, then re-start step 3.4;
It is less than or equal to and then exports non-radial-flow type small power station short term power predictive value Pnrj.
Step 4, according to regional radial-flow type small power station jth moment short term power predictive value PrjWith regional non-radial-flow type small power station
Jth moment short term power predictive value Pnrj, obtain regional small power station's short term power predictive value Pj=Prj+Pnrj.
Claims (9)
1. a kind of small power station classifies short term power Forecasting Methodology, it is characterised in that:It includes
The data message of step 1, the regional radial-flow type small power station of collection and non-radial-flow type water power;
Step 2, by radial-flow type small power station, directly prediction and BP neural network prediction carry out radial-flow type small power station short-term work(respectively
Rate is predicted, and asks for the weight coefficient of two methods predictive value using entropy assessment, calculates the regional radial-flow type small power station jth moment
Short term power predictive value Prj;
Step 3, the regional non-radial-flow type small power station jth moment short term power predictive value P of calculatingnrj;
Step 4, according to regional radial-flow type small power station jth moment short term power predictive value PrjWith regional non-radial-flow type small power station jth
Moment short term power predictive value Pnrj, obtain regional small power station's short term power predictive value Pj=Prj+Pnrj.
2. a kind of small power station according to claim 1 classifies short term power Forecasting Methodology, it is characterised in that:Described in step 1
Collection area radial-flow type small power station data message include meteorological data, go out force data, startup-shutdown data, the meteorological data should
Temperature, air pressure including radial-flow type small power station region, humidity, wind direction, wind speed, rainfall product data;The non-radial-flow type water
The data message of electricity includes meteorological data, goes out force data, the outbound water yield, startup-shutdown data, and meteorological data should include non-radial-flow type
The temperature of water power region, air pressure, humidity, wind direction, wind speed, the medium-term and long-term generating of rainfall product data and non-radial-flow type small power station
Plan and the time-of-use tariffs data of area power grid.
3. a kind of small power station according to claim 1 classifies short term power Forecasting Methodology, it is characterised in that:Described in step 2
Regional radial-flow type small power station jth moment short term power predictive value PrjComputational methods include:
Step 2.1, discharge Q in i-th radial-flow type small power station jth moment of calculatingrij=Qr1ij+Qr2ij, in formula:
Qr1ijRainfall for radial-flow type small power station region;Qr2ijThe outbound water yield for the non-radial-flow type water power in upstream;
Step 2.2, i-th radial-flow type small power station the first short term power of jth moment predictive value P of calculatingr1ij, Pr1ij=ki·Qrij·
HiIn formula:Pr1ijFor i-th radial-flow type small power station the first short term power of jth moment predictive value Pr1ij, unit is W;QrijFor i-th
The discharge in radial-flow type small power station jth moment, unit is m3/s;HiFor the average water head of i-th radial-flow type small power station, unit is
m;kiPower factor for i-th radial-flow type small power station;
Calculate the first short term power predictive value P in regional radial-flow type small power station jth momentr1j;
In formula:N is the total quantity of regional radial-flow type small power station;
Step 2.3, according to i-th radial-flow type small power station meteorological data, go out force data, carry out BP neural network prediction, obtain ground
The second short term power predictive value P in radial-flow type small power station of area jth momentr2j;
Step 2.4, determine Pr1jAnd Pr2jWeight coefficient wr1、wr2, and calculate prediction jth moment day, regional radial-flow type small power station
Short term power predictive value Prj,
Step 2.5, calculating predict that the history of ξ r days a few days ago goes out the error ε of force data and prediction datarIf, continuous ξ r days error
εrRadial-flow type small power station short term power precision of prediction threshold value er for setting is all higher than, re-starts step 2.5;Pre- less than then exporting
Survey jth moment day area radial-flow type small power station short term power predictive value Prj.
4. a kind of small power station according to claim 3 classifies short term power Forecasting Methodology, it is characterised in that:
The method of the second short term power predictive value Pr2j in the regional radial-flow type small power station jth moment described in step 2.3 includes:
Step 2.3.1, three layers of BP neural network are used, the input vector of given BP neural network power prediction model simultaneously returned
One change is processed;The input layer number of the BP neural network power prediction model is 7, according to radial-flow type small power station location
Temperature Tr in the meteorological data in domain, air pressure Pr, humidity Hr, wind direction Wdr, wind speed Wsr, rainfall Qr1, the non-radial-flow type water in upstream
Electric outbound water yield Qr2, forms the input vector Y of BP neural network power prediction modelr=[Tr, Pr, Hr, Wdr, Wsr, Qr1,
Qr2];Described its formula is normalized to input vector Yr it is
Y' in formularijFor jth moment, i-th radial-flow type small power station normalized
Input vector afterwards;YrijFor jth moment, the input vector before i-th radial-flow type small power station normalized;max(Yri) and
min(Yri) represent maximum and the minima of i-th radial-flow type small power station input vector respectively;
Step 2.3.2, selection prediction δ r day data a few days ago are trained to BP neural network, obtain instruction as training sample
BP neural network power prediction model after white silk;
Step 2.3.3, will prediction jth moment day, temperature Tr of i-th radial-flow type small power station regionij, air pressure Prij, humidity
Hrij, wind direction Wdrij, wind speed Wsrij, rainfall Qr1ijOutbound water yield Q with the non-radial-flow type water power in upstreamr2ijAs input layer, defeated
In BP neural network power prediction model after entering to training, output layer data is prediction jth moment day, and i-th radial-flow type is little
Water power the second short term power predictive value pr2ij;
Step 2.3.4, the second short term power predictive value P in calculating regional radial-flow type small power station jth momentr2j
P in formular2ijFor predicting jth moment day, i-th the second short term power of radial-flow type small power station
Predictive value, n is the total quantity of regional radial-flow type small power station.
5. a kind of small power station according to claim 3 classifies short term power Forecasting Methodology, it is characterised in that:Step 2.4 and
Regional radial-flow type small power station short term power predictive value P described in step 2.5rjComputational methods include
Step 2.4.1 is according to prediction θ a few days agorIt history meteorological data and history go out force data, calculate the first short term power respectively
Predictive value Pr1(1)j...Pr1(θr)jWith the second short term power predictive value Pr2(1)j...Pr2j(θr)j, and count actual power value and be
Pr1...Prθr;
Step 2.4.2, respectively with the first short term power predictive value and the error of the second short term power predictive value and actual power value
Absolute value is evaluation index, determines weight coefficient w with entropy assessmentr1And wr2;wr1For Pr1jWeight coefficient, wr2For Pr2jWeight
Coefficient;wr1+wr2=1;
Step 2.4.3, pass through formula Prj=wr1×Pr1j+wr2×Pr2jPrediction jth moment day is calculated, the little water of regional radial-flow type
Electric short term power predictive value Prj;
Step 2.4.4, calculating predict that the history of ξ r days a few days ago goes out the error ε r of force data and prediction data, if continuous ξ r days is by mistake
Difference ε r is all higher than radial-flow type small power station short term power precision of prediction threshold value er for setting, and re-starts step 2.4.3;Less than then defeated
Go out to predict jth moment day, regional radial-flow type small power station short term power predictive value Prj.
6. a kind of small power station according to claim 1 classifies short term power Forecasting Methodology, it is characterised in that:Described in step 3
The non-radial-flow type small power station jth moment short term power predictive value P in calculating areanrjMethod comprise the steps:
Step 3.1, the historical data according to k-th non-radial-flow type small power station of jth moment and meteorological data calculate the jth moment,
K-th non-the first short term power of radial-flow type small power station predictive value Pnr1kj;Pnr1kj=kk·Qnrkj·HkjIn formula:
kkFor the power factor of k-th non-radial-flow type small power station, HkjHead for k-th non-radial-flow type small power station of jth moment;
QnrkjDischarge for k-th non-radial-flow type small power station of jth moment;
Step 3.2, jth moment the first short term power predictive value P of the regional non-radial-flow type small power station of calculatingnr1j;,
In formula:M is the quantity of regional non-radial-flow type small power station;
Step 3.3, in the jth moment, historical data according to the non-radial-flow type small power station of k-th radial-flow type, meteorological data and area
The time-of-use tariffs of electrical network, are calculated the second short term power predictive value of regional non-radial-flow type small power station using support vector machine
Pnr2j;
Step 3.4, determine Pnr1jAnd Pnr2jWeight coefficient wnr1、wnr2, calculate the little water of the non-radial-flow type in prediction jth moment day area
Electric short term power predictive value Pnrj;
ξ a few days ago is predicted in step 3.5, calculatingnrIt history goes out the error ε of force data and prediction datanrIf, continuous ξnrIt is by mistake
Difference εnrIt is all higher than non-radial-flow type small power station short term power precision of prediction threshold value e for settingnr, then re-start step 3.4;It is less than
Or be equal to then export non-radial-flow type small power station short term power predictive value Pnrj.
7. a kind of small power station according to claim 6 classifies short term power Forecasting Methodology, it is characterised in that:Step 3.3 institute
Second short term power predictive value P of the non-radial-flow type small power station in the area statednr2jComputational methods, its step includes:
Step 3.3.1, the input vector of given support vector machine power prediction model are simultaneously normalized;According to non-runoff
The meteorological data of formula small power station region:Temperature Tnr, air pressure Pnr, humidity Hnr, wind direction Wdnr, wind speed WnrsWith rainfall Qnr1、
Time-of-use tariffs Cnr of area power grid, form the input vector Y of support vector machine power prediction modelnr:
Ynr=[Tnr、Pnr、Hnr、Wdnr、Wsnr、Qnr1、Cnr];
Input vector Ynr is normalized, and its formula is:
In formula:Y'nrkjFor jth moment, k-th non-radial-flow type small power station normalized
Input vector afterwards;YnrkjFor jth moment, the input vector before k-th non-radial-flow type small power station normalized;max(Ynrk)
With min (Ynrk) represent the maximum of k-th non-radial-flow type small power station variable and minima respectively;
δ a few days ago is predicted in step 3.3.2, selectionnrIts YnrkjData are trained using support vector machine as training sample, are obtained
Support vector machine power prediction model after must training;
Step 3.3.3, will prediction jth moment day, temperature T of k-th non-radial-flow type small power station regionnrkj, air pressure Pnrkj、
Humidity Hnrkj, wind direction Wdnrkj, wind speed Wsnrkj, rainfall Qnr1kjTime-of-use tariffs C with area power gridnrkjAs input layer, it is input into
In support vector machine power prediction model to after training, output layer data is prediction jth moment day, and k-th non-radial-flow type is little
Water power short term power predictive value pnr2kj;
Step 3.3.4, regional non-radial-flow type small power station jth moment the second short term power predictive value P of calculatingnr2j, its formula is:
8. a kind of small power station according to claim 6 classifies short term power Forecasting Methodology, it is characterised in that:Step 3.4 institute
The P for statingnr1jAnd Pnr2jWeight coefficient wnr1、wnr2Determination method include:
θ a few days ago is predicted in step 3.4.1, acquisitionnrIt history meteorological data and history go out force data;
Step 3.4.2, calculate respectively regional non-radial-flow type small power station first prediction performance number Pnr1(1)j...Pnr1(θnr)jWith second
Power prediction value Pnr2(1)j...Pnr2j(θnr)j;
Step 3.4.3, acquisition actual power value are Pnr1...Pnrθnr;
Step 3.4.4, with predict performance number and actual power value Error Absolute Value as evaluation index, determine weight with entropy assessment
Coefficient wnr1、wnr2, wnr1+wnr2=1.
9. non-radial-flow type small power station short term power weight predicting method according to claim 6, it is characterised in that:Calculate pre-
Survey the non-radial-flow type small power station short term power predictive value P in jth moment day areanrjFormula be:
Pnrj=wnr1×Pnr1j+wnr2×Pnr2j.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610962307.9A CN106447134B (en) | 2016-11-04 | 2016-11-04 | A kind of small power station's classification short term power prediction technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610962307.9A CN106447134B (en) | 2016-11-04 | 2016-11-04 | A kind of small power station's classification short term power prediction technique |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106447134A true CN106447134A (en) | 2017-02-22 |
CN106447134B CN106447134B (en) | 2019-10-15 |
Family
ID=58180993
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610962307.9A Active CN106447134B (en) | 2016-11-04 | 2016-11-04 | A kind of small power station's classification short term power prediction technique |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106447134B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107769268A (en) * | 2017-10-10 | 2018-03-06 | 三峡大学 | Scope is adjusted to predict that province supplies load method a few days ago in a kind of ground containing small power station |
CN109101659A (en) * | 2018-09-03 | 2018-12-28 | 贵州电网有限责任公司 | A kind of method of power data exception in small power station's data collection system |
CN109799864A (en) * | 2019-01-30 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | A kind of region small hydropower station entirety generated power forecasting method and device |
CN109978236A (en) * | 2019-03-04 | 2019-07-05 | 三峡大学 | A kind of small power station's short term power fining prediction technique based on feature combination |
CN111553536A (en) * | 2020-05-06 | 2020-08-18 | 国网安徽省电力有限公司滁州供电公司 | Power grid load prediction method based on multiple energy structures |
CN112462651A (en) * | 2020-11-18 | 2021-03-09 | 贵州电网有限责任公司 | Small hydropower station power prediction method and prediction system considering forebay water level |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104866918A (en) * | 2015-05-07 | 2015-08-26 | 国家电网公司 | Short-term load prediction method of power distribution network with hydropower station |
CN104915736A (en) * | 2015-06-29 | 2015-09-16 | 东北电力大学 | Method for improving accuracy of wind power combined prediction based on improved entropy weight method |
CN105391093A (en) * | 2015-12-07 | 2016-03-09 | 海南电力技术研究院 | Optimal scheduling method for grid-connected operation of small hydropower station group |
-
2016
- 2016-11-04 CN CN201610962307.9A patent/CN106447134B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104866918A (en) * | 2015-05-07 | 2015-08-26 | 国家电网公司 | Short-term load prediction method of power distribution network with hydropower station |
CN104915736A (en) * | 2015-06-29 | 2015-09-16 | 东北电力大学 | Method for improving accuracy of wind power combined prediction based on improved entropy weight method |
CN105391093A (en) * | 2015-12-07 | 2016-03-09 | 海南电力技术研究院 | Optimal scheduling method for grid-connected operation of small hydropower station group |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107769268A (en) * | 2017-10-10 | 2018-03-06 | 三峡大学 | Scope is adjusted to predict that province supplies load method a few days ago in a kind of ground containing small power station |
CN107769268B (en) * | 2017-10-10 | 2021-03-09 | 三峡大学 | Method for predicting provincial supply load day by day in regional dispatching range containing small hydropower stations |
CN109101659A (en) * | 2018-09-03 | 2018-12-28 | 贵州电网有限责任公司 | A kind of method of power data exception in small power station's data collection system |
CN109101659B (en) * | 2018-09-03 | 2021-08-27 | 贵州电网有限责任公司 | Method for power data abnormity in small hydropower station data acquisition system |
CN109799864A (en) * | 2019-01-30 | 2019-05-24 | 云南电网有限责任公司电力科学研究院 | A kind of region small hydropower station entirety generated power forecasting method and device |
CN109978236A (en) * | 2019-03-04 | 2019-07-05 | 三峡大学 | A kind of small power station's short term power fining prediction technique based on feature combination |
CN109978236B (en) * | 2019-03-04 | 2022-07-15 | 三峡大学 | Small hydropower station short-term power refined prediction method based on feature combination |
CN111553536A (en) * | 2020-05-06 | 2020-08-18 | 国网安徽省电力有限公司滁州供电公司 | Power grid load prediction method based on multiple energy structures |
CN112462651A (en) * | 2020-11-18 | 2021-03-09 | 贵州电网有限责任公司 | Small hydropower station power prediction method and prediction system considering forebay water level |
CN112462651B (en) * | 2020-11-18 | 2024-04-26 | 贵州电网有限责任公司 | Small hydropower station power prediction method and prediction system considering front pool water level |
Also Published As
Publication number | Publication date |
---|---|
CN106447134B (en) | 2019-10-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106447134A (en) | Classified short-term power forecast method for small hydropower stations | |
Palma-Behnke et al. | Energy management system for a renewable based microgrid with a demand side management mechanism | |
CN106529718B (en) | A kind of non-radial-flow type small power station short term power weight predicting method | |
CN106875033B (en) | Wind power cluster power prediction method based on dynamic self-adaption | |
CN104167730A (en) | Real-time cascade hydropower stations dispatching optimizing method under complex restrictions | |
CN103400009B (en) | Based on the wind energy turbine set Dynamic Equivalence of the semi-supervised spectral clustering of division level | |
CN104899665A (en) | Wind power short-term prediction method | |
CN107910863A (en) | Consider the power distribution network dispatching method that photovoltaic is contributed with workload demand forecast interval | |
CN106485369B (en) | A kind of radial-flow type small power station short term power weight predicting method | |
CN107609697A (en) | A kind of Wind power forecasting method | |
Gao et al. | Optimal operation modes of photovoltaic-battery energy storage system based power plants considering typical scenarios | |
CN102938562B (en) | Prediction method of total wind electricity power in area | |
CN106655243A (en) | Electric vehicle's automatic demand responding method aiming to maintain the supply-and-demand balance of a micro power grid | |
CN107947244A (en) | The grid-connected power controls in advance method of new energy power station | |
CN103077300A (en) | Forecasting method for generating capacity of distributed photovoltaic power supply on basis of type-2 fuzzy logic | |
CN104732300A (en) | Neural network wind power short-term forecasting method based on fuzzy partition theory | |
CN105159093A (en) | Model-self-adapting-based energy optimal control system of microgrid and design method thereof | |
WO2024051524A1 (en) | Joint prediction method and apparatus for hydraulic, wind and photovoltaic generation power | |
CN104636824A (en) | Distributed photovoltaic siting and sizing method for determining minimum permeability | |
CN106096807A (en) | A kind of complementary microgrid economical operation evaluation methodology considering small power station | |
CN106529716A (en) | Method for power dispatching by using mini hydropower classification short-period power prediction | |
CN107769268A (en) | Scope is adjusted to predict that province supplies load method a few days ago in a kind of ground containing small power station | |
CN106485603A (en) | A kind of short-term wind speed forecasting method being applied to wind-power electricity generation | |
CN108173291A (en) | A kind of distributed new intelligent power distribution method based on weather conditions | |
CN105207255B (en) | A kind of power system peak regulation computational methods suitable for wind power output |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |