CN110147908A - A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm - Google Patents
A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm Download PDFInfo
- Publication number
- CN110147908A CN110147908A CN201910428245.7A CN201910428245A CN110147908A CN 110147908 A CN110147908 A CN 110147908A CN 201910428245 A CN201910428245 A CN 201910428245A CN 110147908 A CN110147908 A CN 110147908A
- Authority
- CN
- China
- Prior art keywords
- day
- wind power
- predicted
- data
- history
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 39
- 241000544061 Cuculus canorus Species 0.000 title claims abstract description 28
- 238000013277 forecasting method Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 241001479919 Ardeola grayii Species 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 244000000626 Daucus carota Species 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000005770 birds nest Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 235000005765 wild carrot Nutrition 0.000 description 1
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
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (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 kind of based on three-dimensional optimal similarity and improves the wind power forecasting method of cuckoo algorithm, including constructing main influence factor matrix, the optimal similarity calculation of multidimensional, the selection of similar day, the improvement of cuckoo algorithm, the training of wind power prediction model and prediction wind power.Go out force data and history environment data by the history that the monitoring system that acquisition is mounted on wind power plant is recorded, n kind influences maximum environmental factor to wind power before being found first using average influence value-based algorithm (MIV), then these data are mapped in n-dimensional space, the selection of similar day is carried out in conjunction with optimal similarity, finally traditional cuckoo algorithm is improved, and improved algorithm is applied in BP neural network, wind power is predicted;This method not only solves selection similar day and only considers the problems of single type weather conditions, and also solving traditional cuckoo algorithm has the problem of limitation.
Description
Technical field
The invention belongs to power system and automation technologies, and in particular to one kind based on three-dimensional optimal similarity with
Improve the wind power forecasting method of cuckoo algorithm.
Background technique
Since China has a vast territory, seashore wire length, so wind energy resources are very abundants in China, therefore wind energy resources
Following national strategy stored energy source will be become.Moreover, as the continuous development of wind power technology and the scale of wind power plant are continuous
Increase, in order to guarantee the stable operation and power supply reliability of electric system, wind power system is effectively planned and scheduling is
It is of great significance.However the randomness and uncertainty due to wind speed lead to wind power output fluctuation acutely, to the peace of power grid
Full stable operation proposes challenge.Therefore, adjustment in time is changed according to wind power in order to enable electric dispatching department to shift to an earlier date
Operation plan guarantees power quality, reduces the spare capacity of system, reduces Operation of Electric Systems cost, mitigates wind-power electricity generation pair
Adverse effect caused by power grid improves power grid apoplexy Denso machine ratio, it is necessary to predict the output power of wind power plant.
It mainly include physical method and statistical method currently, having there is many domestic and foreign scholars to do a lot of research work.
Wherein physical method needs to have more physical parameter relevant to blower and other information, and model is complicated.Statistical method is only
Need to the time series to wind speed and power can predict.Common are regression analysis, artificial neural network method, support to
Amount machine method, gray forecast approach, all multi-methods of combinatorial forecast.Now, similar day has been applied in wind power prediction, still
The general method for choosing similar day is added by comparing single factors or by the similar value of several single factors, these sides
All there is limitations for method: not accounting for the influence that mixed influence factor pair chooses similar day.And in numerous prediction techniques
In, BP neural network is a kind of more commonly used prediction technique.But the convergence rate of BP neural network prediction technique is slower,
It is easily trapped into local extremum, cuckoo algorithm can fall into locally optimal solution to avoid algorithm, also have stronger global search energy
Power, therefore there is scholar to optimize using weight and threshold value of the cuckoo algorithm to BP neural network.However, cuckoo algorithm
It is poor that there are convergence capabilities, search vigor it is insufficient the disadvantages of, in order to avoid these defects, it is necessary to choose similar historical day and
Wind power forecasting method does further research and improves.
Summary of the invention
The purpose of the present invention is to provide a kind of based on three-dimensional optimal similarity and improves the wind power of cuckoo algorithm
Prediction technique, poor, search vigor deficiency etc. that there is also convergence capabilities to solve cuckoo algorithm mentioned above in the background art
The problem of disadvantage.
To achieve the above object, the invention provides the following technical scheme: it is a kind of based on three-dimensional optimal similarity and improvement cloth
The wind power forecasting method of paddy bird algorithm, comprising the following steps:
Step 1: main influence factor matrix is constructed: in wind power plant installation monitoring system, and the recorded wind power plant of acquisition system
Meteorological data and history wind power data, using every 30min as a sample, acquire day to be predicted and two
Daily data in month, wherein meteorological data includes: cloud amount, temperature, humidity, wind speed and precipitation, utilizes Mean Impact Value
Algorithm (MIV) finds n kind influence factor maximum to wind power disturbance degree, constructs history day wind-powered electricity generation according to these influence factors
The main influence factor matrix A of poweri=[ai1 ai2 … ain], wherein ainIndicate i-th day n-th principal impact factor feature to
Amount,
In formula, ain(k) it indicates the under i-th day n-th principal impact factor vector
The value at x time point;
Step 2: the optimal similarity calculation of multidimensional: using identical with principal impact factor in the day to be predicted in step 1
Weather category data construct the meteorological factor matrix A of day to be predicted0=[a01 a02 … a0n], wherein a0nFor in day to be predicted
The feature vector of n-th of meteorological factor,In formula, aon(x) day to be predicted the is indicated
The value at x-th of time point under n meteorological factor vector;Calculate history day main influence factor matrix and day to be predicted it is meteorological because
The mean vector of submatrixWithWhereinWithFor history
The average value of day and day to be predicted daily n-th of meteorological factor;According to formulaEach go through is calculated
The shape coefficient of the optimal similarity of multidimensional of Shi and day to be predicted, whereinI=1,2,3 ..., 60,According to formulaIt calculates
Obtain the value coefficient of the optimal similarity of multidimensional of each history day and day to be predicted;The shape coefficient acquired and value are combined in conjunction with acquiring
Coefficient finds out the optimal similarity λ of multidimensional of history day Yu day to be predictedi, and λi=Fi*Di;
Step 3: the selection of similar day: descending sequence is carried out to the optimal similarity of multidimensional that step 2 is found out, is obtained
To corresponding similar day sequence date=[date1 date2 … date60], according to similar day sequence, select the optimal phase of multidimensional
It is higher than 0.8 preceding 10 days similar days as day to be predicted like degree;
Step 4: the improvement of cuckoo algorithm: based on abandoning probability ρ and step factor in cuckoo algorithmAccording to
Formula
It improves;
Step 5: the training of wind power prediction model: the data of similar day are normalized, by main influence because
Element as input, history generated output as output, be put into based on step 4 improve cuckoo algorithm BP neural network in into
Row training;
Step 6: prediction wind power: the data of day to be predicted are normalized, and by the meteorology after normalization
Data are put into the prediction model obtained by step 5 and predict the wind power of day to be predicted, then by the output valve of model
Anti-normalization processing is carried out, the wind power prediction value of day to be predicted is obtained.
Further, it is 7:00-17:00 that the specific data in day and two month to be predicted are acquired in the step 1
The data of period.
Compared with prior art, the beneficial effects of the present invention are: selection similar day can be removed in conjunction with various factors, also
The poor disadvantage of traditional cuckoo Algorithm Convergence can be overcome, can be very good the speed for improving wind power prediction model
Degree and precision, for the safe and stable operation of power grid, the economical operation of system is of great significance.
Detailed description of the invention
Fig. 1 is that the present invention is a kind of based on three-dimensional optimal similarity and the wind power forecasting method for improving cuckoo algorithm
The flow chart of wind power forecasting method.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment
As shown in Figure 1, a kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm, packet
Include following steps:
Step 1: the method for constructing main influence factor matrix: in wind power plant installation monitoring system, and acquisition system is recorded
The meteorological data of wind power plant and the data of history wind power, using every 30min as a sample, acquire day to be predicted and
Daily in the data of 7:00-17:00 in two month, wherein meteorological data includes: cloud amount, temperature, humidity, wind speed and precipitation
Amount, finds n kind influence factor maximum to wind power disturbance degree using average influence value-based algorithm (MIV), according to these influences
The main influence factor matrix A of factor building history day wind poweri=[ai1 ai2 … ain], wherein ainIt indicates i-th day n-th
The feature vector of principal impact factor,
In formula, ain(k) it indicates under i-th day n-th principal impact factor vector
The value at x-th of time point;
Step 2: the optimal similarity calculation of multidimensional:
(1) is constructed to be predicted using weather category data identical with principal impact factor in the day to be predicted in step 1
The meteorological factor matrix A of day0=[a01 a02 … a0n], wherein a0nFor the feature vector of n-th of meteorological factor in day to be predicted,In formula, aon(x) when indicating under n-th of meteorological factor vector of day to be predicted x-th
Between the value put;
(2) calculates the mean vector of the main influence factor matrix of history day and the meteorological factor matrix of day to be predictedWithWhereinWithIt is daily for history day and day to be predicted
The average value of n-th of meteorological factor;
(3) is according to formulaMultidimensional optimal phase of each history day with day to be predicted is calculated
Like the shape coefficient of degree, whereinI=1,2,3 ...,
60,
(4) is according to formulaIt is optimal similar to the multidimensional of day to be predicted that each history day is calculated
The value coefficient of degree;
(5) is acquired in conjunction with (3) and (4) in conjunction with the shape coefficient and value coefficient that acquire, finds out the more of history day and day to be predicted
Tie up optimal similarity λi, and λi=Fi*Di;
Step 3: the selection of similar day: descending sequence is carried out to the optimal similarity of multidimensional that step 2 is found out, is obtained
To corresponding similar day sequence date=[date1 date2 … date60], according to similar day sequence, select the optimal phase of multidimensional
It is higher than 0.8 preceding 10 days similar days as day to be predicted like degree;
Step 4: the process and method of wind power prediction model training:
(1) tradition cuckoo algorithm haves the shortcomings that convergence rate is slower, and for abandoning probability ρ, at the beginning of iteration
Phase must keep ρ larger, the iteration later period arrived, in order to accelerate algorithm to increase in initial stage Bird's Nest position preferably quantity
Convergence, ρ should take lesser value.And for step factorIn order to avoid falling into locally optimal solution at iteration initial stage, soBiggish value should be taken, the iteration later period has been arrived, in order to reinforce the ability in local search optimal solution,Smaller value, cloth should be taken
Probability ρ and step factor are abandoned in paddy bird algorithmAccording to formula
It improves;
(2) carries out data normalization processing, with formulaTo the meteorological number of history day and day to be predicted
Accordingly and wind power data are normalized, wherein xmaxAnd xminRespectively indicate maximum value in homogeneous data and most
Small value, x indicate the actual value of data, and y indicates the normalized value of data;
(3) is optimized according to weight and threshold value of the cuckoo algorithm improved in (1) to BP neural network;It will be in (2)
Data set be put into improve cuckoo algorithm optimization BP neural network model in be trained, obtain the predicted value of wind power.
Step 5: it the process and method of the anti-normalization processing of prediction model output prediction result: will be obtained in step 4
Wind power predicted value according to formula x=xmax-y.(xmax-xmin) carry out anti-normalization processing.
The working principle of the invention and process for using: all types of environmental factors for influencing wind power are considered, by adopting
The history that the monitoring system that collection is mounted on wind power plant is recorded goes out force data and history environment data, uses average influence first
N kind influences maximum environmental factor to wind power before value-based algorithm (MIV) is found, these data are then mapped to n-dimensional space
In, the selection of similar day is carried out in conjunction with optimal similarity, finally traditional cuckoo algorithm is improved, and will be improved
Algorithm is applied in BP neural network, is predicted wind power;This method not only solves selection similar day and only considers list
The problem of type weather conditions, also solving traditional cuckoo algorithm has the problem of limitation.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (2)
1. a kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm, it is characterised in that: packet
Include following steps:
Step 1: main influence factor matrix is constructed: in wind power plant installation monitoring system, and the gas of the recorded wind power plant of acquisition system
The data of image data and history wind power are acquired in day to be predicted and two moon using every 30min as a sample
Daily data, wherein meteorological data includes: cloud amount, temperature, humidity, wind speed and precipitation, utilizes average influence value-based algorithm
(MIV) n kind influence factor maximum to wind power disturbance degree is found, constructs history day wind power according to these influence factors
Main influence factor matrix Ai=[ai1 ai2 … ain], wherein ainIndicate the feature vector of i-th day n-th principal impact factor,
In formula, ain(k) it indicates under i-th day n-th principal impact factor vector x-th
The value at time point;
Step 2: the optimal similarity calculation of multidimensional: meteorology identical with principal impact factor in the day to be predicted in step 1 is utilized
Categorical data constructs the meteorological factor matrix A of day to be predicted0=[a01 a02 … a0n], wherein a0nIt is n-th in day to be predicted
The feature vector of meteorological factor,
In formula, aon(x) xth under n-th of meteorological factor vector of day to be predicted is indicated
The value at a time point;Calculate the mean vector of the main influence factor matrix of history day and the meteorological factor matrix of day to be predictedWithWhereinWithFor history day and day to be predicted daily
The average value of n meteorological factor;According to formulaThe more of each history day and day to be predicted are calculated
Tie up the shape coefficient of optimal similarity, wherein
According to formulaMeter
It calculates and obtains the value coefficient of the optimal similarity of multidimensional of each history day and day to be predicted;In conjunction with acquiring in conjunction with the shape coefficient that acquires and
Value coefficient finds out the optimal similarity λ of multidimensional of history day Yu day to be predictedi, and λi=Fi*Di;
Step 3: the selection of similar day: carrying out descending sequence to the optimal similarity of multidimensional that step 2 is found out, and obtains pair
The similar day sequence date=[date answered1 date2 … date60], according to similar day sequence, select the optimal similarity of multidimensional
Preceding 10 days similar days as day to be predicted higher than 0.8;
Step 4: the improvement of cuckoo algorithm: based on abandoning probability ρ and step factor in cuckoo algorithmAccording to formula
It improves;
Step 5: the training of wind power prediction model: the data of similar day are normalized, and main influence factor is made
For input, history generated output is put into the BP neural network for being improved cuckoo algorithm based on step 4 and is instructed as output
Practice;
Step 6: prediction wind power: the data of day to be predicted are normalized, and by the meteorological data after normalization
It is put into the prediction model obtained by step 5 and the wind power of day to be predicted is predicted, then the output valve of model is carried out
Anti-normalization processing obtains the wind power prediction value of day to be predicted.
2. a kind of wind power prediction based on three-dimensional optimal similarity and improvement cuckoo algorithm according to claim 1
Method, it is characterised in that: it is 7:00-17:00 that the specific data in day and two month to be predicted are acquired in the step 1
The data of period.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910428245.7A CN110147908A (en) | 2019-05-22 | 2019-05-22 | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910428245.7A CN110147908A (en) | 2019-05-22 | 2019-05-22 | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110147908A true CN110147908A (en) | 2019-08-20 |
Family
ID=67592641
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910428245.7A Pending CN110147908A (en) | 2019-05-22 | 2019-05-22 | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110147908A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598947A (en) * | 2019-09-20 | 2019-12-20 | 东莞理工学院 | Load prediction method based on improved cuckoo-neural network algorithm |
CN110619360A (en) * | 2019-09-09 | 2019-12-27 | 国家电网有限公司 | Ultra-short-term wind power prediction method considering historical sample similarity |
CN112307672A (en) * | 2020-10-29 | 2021-02-02 | 上海电机学院 | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9118182B2 (en) * | 2012-01-04 | 2015-08-25 | General Electric Company | Power curve correlation system |
CN105447572A (en) * | 2015-12-21 | 2016-03-30 | 广东智造能源科技研究有限公司 | Wind power prediction system and method based on neural network optimized by genetic algorithm |
CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学(保定) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
CN108197744A (en) * | 2018-01-02 | 2018-06-22 | 华北电力大学(保定) | A kind of determining method and system of photovoltaic generation power |
CN109034484A (en) * | 2018-08-02 | 2018-12-18 | 广东工业大学 | A kind of wind speed forecasting method, device and equipment |
CN109034464A (en) * | 2018-07-11 | 2018-12-18 | 南京联迪信息***股份有限公司 | A kind of method that short-term photovoltaic generating system power prediction and result are checked |
-
2019
- 2019-05-22 CN CN201910428245.7A patent/CN110147908A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9118182B2 (en) * | 2012-01-04 | 2015-08-25 | General Electric Company | Power curve correlation system |
CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学(保定) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
CN105447572A (en) * | 2015-12-21 | 2016-03-30 | 广东智造能源科技研究有限公司 | Wind power prediction system and method based on neural network optimized by genetic algorithm |
CN108197744A (en) * | 2018-01-02 | 2018-06-22 | 华北电力大学(保定) | A kind of determining method and system of photovoltaic generation power |
CN109034464A (en) * | 2018-07-11 | 2018-12-18 | 南京联迪信息***股份有限公司 | A kind of method that short-term photovoltaic generating system power prediction and result are checked |
CN109034484A (en) * | 2018-08-02 | 2018-12-18 | 广东工业大学 | A kind of wind speed forecasting method, device and equipment |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110619360A (en) * | 2019-09-09 | 2019-12-27 | 国家电网有限公司 | Ultra-short-term wind power prediction method considering historical sample similarity |
CN110598947A (en) * | 2019-09-20 | 2019-12-20 | 东莞理工学院 | Load prediction method based on improved cuckoo-neural network algorithm |
CN112307672A (en) * | 2020-10-29 | 2021-02-02 | 上海电机学院 | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11581740B2 (en) | Method, system and storage medium for load dispatch optimization for residential microgrid | |
CN105046374B (en) | A kind of power interval prediction technique based on core extreme learning machine model | |
CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
CN109858673A (en) | A kind of photovoltaic generating system power forecasting method | |
CN106295899B (en) | Wind power probability density Forecasting Methodology based on genetic algorithm Yu supporting vector quantile estimate | |
CN107423852A (en) | A kind of light storage combined plant optimizing management method of meter and typical scene | |
CN106351793A (en) | System and method for improved wind power generation | |
CN102184453A (en) | Wind power combination predicting method based on fuzzy neural network and support vector machine | |
CN102478584B (en) | Wind power station wind speed prediction method based on wavelet analysis and system thereof | |
CN107528350B (en) | A kind of wind power output typical scene generation method adapting to long -- term generation expansion planning | |
CN105373857A (en) | Photovoltaic power station irradiance prediction method | |
CN110147908A (en) | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm | |
CN109886567B (en) | Short-term load prediction method considering somatosensory temperature and radiation intensity | |
CN107609716B (en) | A kind of power station load setting prediction technique | |
CN103473621A (en) | Wind power station short-term power prediction method | |
CN108596242A (en) | Power grid meteorology load forecasting method based on wavelet neural network and support vector machines | |
CN109376950A (en) | A kind of polynary Load Forecasting based on BP neural network | |
CN107679687A (en) | A kind of photovoltaic output modeling method and Generation System Reliability appraisal procedure | |
CN102479347A (en) | Method and system for forecasting short-term wind speed of wind farm based on data driving | |
CN105846425A (en) | Economic dispatching method based on general wind power forecasting error model | |
CN108075471B (en) | Multi-objective constraint optimization power grid scheduling strategy based on stochastic power output prediction | |
CN105046349B (en) | It is a kind of meter and wake effect wind power forecasting method | |
CN114021848A (en) | Generating capacity demand prediction method based on LSTM deep learning | |
CN109242200A (en) | A kind of wind power interval prediction method of Bayesian network forecasting model | |
Lu et al. | Wind power forecast by using improved radial basis function neural network |
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 |