CN108197744A - A kind of determining method and system of photovoltaic generation power - Google Patents
A kind of determining method and system of photovoltaic generation power Download PDFInfo
- Publication number
- CN108197744A CN108197744A CN201810001865.8A CN201810001865A CN108197744A CN 108197744 A CN108197744 A CN 108197744A CN 201810001865 A CN201810001865 A CN 201810001865A CN 108197744 A CN108197744 A CN 108197744A
- Authority
- CN
- China
- Prior art keywords
- history
- day
- photovoltaic generation
- generation power
- meteorological data
- 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 34
- 238000005457 optimization Methods 0.000 claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 230000001537 neural effect Effects 0.000 claims description 38
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000006872 improvement Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 5
- 210000004218 nerve net Anatomy 0.000 claims description 3
- 239000013598 vector Substances 0.000 description 12
- 230000000694 effects Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 5
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 230000017105 transposition 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Photovoltaic Devices (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of determining method and system of photovoltaic generation power.The present invention is based on mind evolutionary optimization radial basis neural network is improved, the history similar day of prediction day is obtained on the basis of each influence factor weight is considered, it is more reasonable to the selection of meteorologic factor (i.e. impact factor)；Make similar day selection algorithm more efficient；Similar day data predict prediction day photovoltaic generation power using mind evolutionary optimization radial basis neural network is improved, determine the photovoltaic generation power of day to be measured with prediction day meteorological data as input.Error during determining photovoltaic generation power can be reduced using determining method and system provided by the present invention.
Description
Technical field
The present invention relates to field of power, more particularly to a kind of determining method and system of photovoltaic generation power.
Background technology
In recent years, China becomes the global fastest-rising country of photovoltaic generation erecting device, domestic photovoltaic generation market
Just developed from stand alone generating system to grid-connected system.Photovoltaic generation power has intermittence since day alternates with night, is bullied
As etc. factors influence with fluctuation, randomness, therefore accurately determine photovoltaic generation power in advance, ensure photovoltaic generation simultaneously
The reliable and stable operation of power grid is the most important thing of photovoltaic power generation technology development in network process.
The research determined in advance in short term to photovoltaic generation power at present is generally required comprising crucial meteorologic factor and irradiation level
Numerical weather forecast, and using neural network, classification recurrences, time series, the calculation of the photovoltaic power generation power predictions such as wavelet analysis
Method is predicted.But many documents lack the selection of meteorologic factor Theoretical analysis, and the selection course of similar day does not account for
The Weight of each meteorologic factor (i.e. impact factor) is to carry out analysis choosing to each meteorologic factor in the prior art therefore
It selects, there are many obtained similar day similar to day meteorological data to be measured, so as to cause the photovoltaic generation power determined in advance
Error is big.
Invention content
The object of the present invention is to provide a kind of determining method and system of photovoltaic generation power, to solve to carry in the prior art
The problem of preceding determining photovoltaic generation power error is big.
To achieve the above object, the present invention provides following schemes：
A kind of determining method of photovoltaic generation power, including：
Obtain history meteorological data and history photovoltaic generation power；The history meteorological data includes temperature, humidity, spoke
Illumination, wind speed, wind direction；
Impact factor is determined according to the history meteorological data and the history photovoltaic generation power；The impact factor
Including temperature, humidity, irradiation level；
The weight of the impact factor is determined according to the history photovoltaic generation power；
Obtain the day meteorological data to be measured of day to be measured；
The history day for being higher than similarity threshold with the similarity of the day meteorological data to be measured is determined according to the weight；
Obtain the history day meteorological data and history day photovoltaic generation power of the history day；
The initial weight and threshold value of radial base neural net are optimized, the radial direction base nerve net after being optimized
Network；
Using the history day meteorological data as the input of the radial base neural net after the optimization, with history day photovoltaic
Output of the generated output as the radial base neural net after the optimization establishes and improves mind evolutionary optimization radial direction base god
Through network model；
The day meteorological data to be measured is input to the improvement mind evolutionary optimization radial basis neural network,
Export the photovoltaic generation power of day to be measured.
It is optionally, described that impact factor is determined according to the history meteorological data and the history photovoltaic generation power,
It specifically includes：
The history meteorological data and the history photovoltaic generation power are normalized, obtain that treated
History meteorological data-history photovoltaic generation power relationship；
Impact factor is determined according to the history meteorological data-history photovoltaic generation power relationship.
Optionally, the weight that the impact factor is determined according to the history photovoltaic generation power, specifically includes：
Correlation analysis is carried out to the impact factor and the history photovoltaic generation power, obtains history photovoltaic generation
Related coefficient between power and the history meteorological data；
According to the related coefficient, the impact factor is determined using average influence value-based algorithm；
The weight of the impact factor is determined according to entropy assessment.
Optionally, it is described to be determined to be higher than similarity threshold with the similarity of the day meteorological data to be measured according to the weight
History day, specifically include：
According to the weight, determine to be higher than phase with the similarity of the day meteorological data to be measured using optimal Similar operator
Like the history day of degree threshold value.
Optionally, the initial weight and threshold value to radial base neural net optimizes, the diameter after being optimized
To base neural net, specifically include：
The initial weight and threshold value of radial base neural net are optimized using mind evolutionary is improved, obtained
Radial base neural net after to optimization.
A kind of determining system of photovoltaic generation power, including：
First acquisition module, for obtaining history meteorological data and history photovoltaic generation power；The history meteorology number
According to including temperature, humidity, irradiation level, wind speed, wind direction；
Impact factor determining module, for being determined according to the history meteorological data and the history photovoltaic generation power
Impact factor；The impact factor includes temperature, humidity, irradiation level；
Weight determination module, for determining the weight of the impact factor according to the history photovoltaic generation power；
Day meteorological data acquisition module to be measured, for obtaining the day meteorological data to be measured of day to be measured；
History day determining module, for according to the weight determine with the similarity of the day meteorological data to be measured be higher than phase
Like the history day of degree threshold value；
Second acquisition module, for obtaining the history day meteorological data and history day photovoltaic generation work(of the history day
Rate；
Optimization module optimizes for the initial weight to radial base neural net and threshold value, after being optimized
Radial base neural net；
Model building module, for using the history day meteorological data as the radial base neural net after the optimization
Input, using history day photovoltaic generation power as the radial base neural net after the optimization output, establish improve thinking into
Change algorithm optimization radial basis neural network；
Photovoltaic generation power determining module is calculated for the day meteorological data to be measured to be input to the improvement mind-evolution
Method optimizes radial basis neural network, exports the photovoltaic generation power of day to be measured.
Optionally, the impact factor determining module specifically includes：
Normalized unit, for carrying out normalizing to the history meteorological data and the history photovoltaic generation power
Change is handled, the history meteorological data-history photovoltaic generation power relationship that obtains that treated；
The first determination unit of impact factor, for true according to the history meteorological data-history photovoltaic generation power relationship
Determine impact factor.
Optionally, the weight determination module specifically includes：
Dependency analysis unit, for carrying out correlation point to the impact factor and the history photovoltaic generation power
Analysis, obtains the related coefficient between history photovoltaic generation power and the history meteorological data；
The second determination unit of impact factor, for according to the related coefficient, being determined using average influence value-based algorithm described
Impact factor；
The second determination unit of weight, for determining the weight of the impact factor according to entropy assessment.
Optionally, the history day determining module specifically includes：
History day determination unit, for according to the weight, being determined and the day gas to be measured using optimal Similar operator
The similarity of image data is higher than the history day of similarity threshold.
Optionally, the optimization module specifically includes：
Optimize unit, for improving initial weight and threshold of the mind evolutionary to radial base neural net using improvement
Value optimizes, the radial base neural net after being optimized.
According to specific embodiment provided by the invention, the invention discloses following technique effects：The present invention provides one kind
The determining method and system of photovoltaic generation power, according to history meteorological data and history photovoltaic generation power determine influence because
Son selectively selects all history days higher with day meteorological data similarity to be measured according to the weight of impact factor, from
And can more accurately determine the photovoltaic generation power of day to be measured, reduce error.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the determining method flow diagram of photovoltaic generation power provided by the present invention；
Fig. 2 is the comparison diagram of photovoltaic generation power provided by the present invention that June 30,4 kinds of modes obtained；
Fig. 3 is the determining system construction drawing of photovoltaic generation power provided by the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide a kind of determining method and system of photovoltaic generation power, can reduce determining day to be measured
Photovoltaic generation power error, improve the precision of prediction of photovoltaic generation power.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
The present invention is had fluctuation and stochastic problems for photovoltaic generation power by meteorological factor influence, based on improvement
Mind evolutionary (improved mind evolutionary algorithm, IMEA) optimization radial basis function (radical
Basis function, RBF) mode short-term photovoltaic generation power is predicted, utilize correlation analysis and average influence
Being worth (mean impact value, MIV), the corresponding meteorologic factor of algorithm picks is as input pointer, by considering the optimal of weight
The similar day of prediction day is calculated in Similar operator, using similar day data with prediction day meteorological data as inputting, using changing
Optimize radial basis neural network into mind evolutionary to predict prediction day photovoltaic generation power, so as to improve to light
Lie prostrate the precision of prediction of generated output.
Fig. 1 is the determining method flow diagram of photovoltaic generation power provided by the present invention, as shown in Figure 1, a kind of photovoltaic is sent out
The determining method of electrical power, including：
Step 101：Obtain history meteorological data and history photovoltaic generation power；The history meteorological data includes temperature
Degree, humidity, irradiation level, wind speed, wind direction.
Step 102：Impact factor is determined according to the history meteorological data and the history photovoltaic generation power；It is described
Impact factor includes temperature, humidity, irradiation level.
The step 102 specifically includes：The history meteorological data and the history photovoltaic generation power are returned
One change is handled, the history meteorological data-history photovoltaic generation power relationship that obtains that treated；According to the history meteorological data-
History photovoltaic generation power relationship determines impact factor.
Step 103：The weight of the impact factor is determined according to the history photovoltaic generation power.
The step 103 specifically includes：Correlation is carried out to the impact factor and the history photovoltaic generation power
Analysis, obtains the related coefficient between history photovoltaic generation power and the history meteorological data；According to the related coefficient, adopt
The impact factor is determined with average influence value-based algorithm；The weight of the impact factor is determined according to entropy assessment.
The selection of impact factor
After data normalization is handled to photovoltaic generation power and temperature, humidity, irradiation level, wind speed, wind direction 5 it is meteorological because
Correlation analysis is carried out between element, obtains related coefficient of the daily photovoltaic generation power with corresponding meteorologic factor.Pass through correlation
The calculating of coefficient can get rid of wind direction, and wind speed is larger with the related coefficient of power within some periods, only passes through correlation
Property analysis is bad directly ignores wind speed this meteorologic factor, therefore use average influence value-based algorithm (Mean Impact Value,
MIV the selection that following model inputs meteorological factor) is carried out by BP neural network.Its concrete application step is as follows：
1) 4 meteorologic factors are formed into training sample S, S=[X1；X2；X3；X4], X1To X4Respectively represent temperature, humidity,
4 irradiation level, wind speed meteorologic factor vectors, photovoltaic generation power P are exported as network.After network training, by training
Each meteorologic factor in sample S adds and subtracts 10% respectively on the basis of initial value, forms new training sample S1, S2。
2) by S1, S2It is emulated respectively as simulation sample using built network, obtains two simulation result F1、
F2, F is obtained1、F2Difference be the influence changing value (Impact Value, IV) for changing and being generated to output after the independent variable, most
IV is averagely shown that the meteorologic factor corresponds to the MIV of dependent variable network output by observation number of cases afterwards.
3) it after calculating the corresponding MIV values of 4 meteorologic factors, obtains after sorting by MIV orders of magnitude to 4 meteorologic factors
To network output relative importance precedence.
According to above-mentioned steps, obtain temperature, humidity, irradiation level, 4 meteorologic factors of wind speed MIV values be respectively 0.324,
0.128、0.408、0.003.Wherein the MIV value highests of irradiation level, the MIV values of temperature and humidity are taken second place, and the MIV values of wind speed with
First three meteorologic factor is not in an order of magnitude.Therefore, by the MIV indexs of BP neural network, temperature, humidity, spoke are selected
Illumination inputs meteorologic factor as following model, and wind speed is not as input meteorologic factor.
Step 104：Obtain the day meteorological data to be measured of day to be measured.
Step 105：It is determined according to the weight with the similarity of the day meteorological data to be measured higher than similarity threshold
History day.
The step 105 specifically includes：According to the weight, determined and the day gas to be measured using optimal Similar operator
The similarity of image data is higher than the history day of similarity threshold.
Using optimal Similar operator, determine that each meteorologic factor weight carries out the choosing of day similar day to be predicted with reference to entropy assessment
It selects.Daily Meteorological Characteristics vector is denoted as Xi=[Xi1, Xi2, Xi3]T, i expressions i-th day, wherein, Xi1=[Xi1(1), Xi1
(2)...Xi(n)]TRepresent daily temperature vector；Xi2=[Xi2(1), Xi2(2)...Xi2(n)]TRepresent daily humidity vector,
Wherein T is the transposition of matrix；Xi3=[Xi3(1), Xi3(2)...Xi3(n)]TRepresent daily solar irradiance vector.It is to be predicted
The Meteorological Characteristics vector of day is X0=[X01, X02, X03]T.Weight shared by three Meteorological Characteristics vectors is calculated by entropy assessment, it is main
It is divided into following two step：
1) comentropy of each feature vector is sought
Wherein, YijRepresent Xi(j), under (j=1,2 ..., n) index, a Meteorological Characteristics vectors of i-th (i=1,2,3) are commented
Value；
Wherein, PijIt is the proportion of the index value of i-th of Meteorological Characteristics vector under j-th of index；
If pij=0, then it defines
2) each index weights are determined
According to the calculation formula of comentropy, the comentropy for calculating each Meteorological Characteristics vector is E1,E2,...,Ek.Pass through
Comentropy calculates the weight of each index：
Optimal Similar operator mainly comprises the following steps：
1) the shape coefficient of optimal similarity factor is sought
2) value coefficient of optimal similarity factor is sought
Vijk=e-Dijk (5)
3) with reference to shape coefficient and value coefficient, optimal similarity factor is sought
BFVijk=Fijk·Vijk (7)
4) the optimal similarity factor of comprehensive all impact factors, then day to be predicted be with history day i similarities
At this point, j represents 3 Meteorological Characteristics vectors
5) according to similarity value λiSize it is descending sequence obtain the similar day sequence D of day to be predictedi=[d1,
d2...di], a part for wherein similarity value maximum is chosen as similar day, wherein, diRepresent day serial number.
Step 106：Obtain the history day meteorological data and history day photovoltaic generation power of the history day.
Step 107：The initial weight and threshold value of radial base neural net are optimized, the radial direction base after being optimized
Neural network.
The step 107 specifically includes：Initial power of the mind evolutionary to radial base neural net is improved using improvement
Value and threshold value optimize, the radial base neural net after being optimized.
Weights of the initial weight for radial base neural net hidden layer to output layer；The threshold value is radial direction base nerve
It is used to adjust the parameter of neuron sensitivity in network.
Step 108：Using the history day meteorological data as the input of the radial base neural net after the optimization, to go through
Output of the photovoltaic generation power as the radial base neural net after the optimization of history day establishes and improves mind evolutionary optimization
Radial basis neural network.
Improve mind evolutionary
Evolution thinking algorithm carries out two-wheeled individual distribution respectively in Population Initialization procedure, is obtained in the individual that the first round spreads
The high several body of score value forms winning sub-group, and the high several body of score forms interim subgroup during the second wheel individual is spread
Body.The serial number of oneself, action and score information are posted on local advertisements plate and global advertisement plate by individual respectively with sub-group.
During evolution, in the range of sub-group, the process that individual competes to become winner is referred to as convergent；In entire solution space
In, each sub-group constantly detects new point in competition process, is substituted with the interim sub-group that score is more than winning sub-group winning
The process of sub-group is known as alienation.
It is convergent particularly significant with alienation strategy in evolution thinking algorithm, improved convergent and alienation strategy is proposed respectively.
1) the convergent strategy of dynamic
Convergent process is by spreading a new generation's individual by normal distribution near the winner of sub-group prior-generation, starting
The individual score of a new round calculates, and generates new winning sub-group.Wherein, the sub-group scale spread near winner according to
The score height dynamic of winning individual obtains, and it is attached that individual of new generation will more be dispersed in the higher winning individual of previous generation scores
Closely, it is as follows to calculate step：
1. calculate individual x in the winning sub-group containing n individuali(i=1,2 ..., n) it is scored at si(i=1,
2,...,n)；
2. with xiCentered on, obey X~N (μ, σ2) spread MiA new individual, wherein μ are mathematic expectaion, and σ is standard variance,
L≤Mi≤ H, wherein, L be the variable upper limit, H be variable lower limit, MiFor new individual；Then：
3. the sub-group of new individual composition a new generation generated as stated above.
Variance in normal distribution is obtained according to distance between adjacent winning individual of evolving twice with score value difference dynamic, when two
Distance is short between the winning individual of secondary evolution, and when score difference is big, variance reduces, fine search optimum point, otherwise, variance increase,
Rough search optimum point.If the adjacent winning individual evolved twice is respectively to be scored at s in the Ω of regionm kXm kBe scored at sn k+1
Xn k+1, the calculating step of dynamic variance is as follows：
1. calculate it is adjacent evolve twice it is winning individual apart from perunit value
Wherein, i, j represent the adjacent i individual evolved twice and j individual respectively, and m, n are excellent in evolving twice
Win the serial number of individual；
2. calculate the perunit value of the adjacent point spread of evolution twice
3. obtain dynamic variance
σk+1=σk·(d1/d2) (12)
2) simplex alienation strategy
If winning sub-group has n+1, xiThe n+1 vertex for simplex.I=0,1 ..., n
1. it reflects
Worst sub-group score
Wherein, h is the abbreviation of high, i.e.,：Functional value maximum is worst, meets the x of this formulaiIt is denoted as xh。
Secondary difference sub-group score
Wherein, s is represented between high sub-group and low sub-group.
Optimal sub-group score
L is the abbreviation of low, i.e.,：Functional value minimum is optimal.
X is removed in calculatinghThe centre of form on all vertex afterwards
Calculate xhPip xr
xr=2xc-xh (17)
2. it expands
If f (xr) ＜ fl, then enable
xe=xc+α(xc-xh), (α ＞ 1) (18)
α is flare factor, is exactly amplification, takes a value for being more than 1, generally takes 2.
If f (xe) ＜ f (xr), use xeSubstitute xhIt is returned 1) after forming new winning sub-group, conversely, using xrInstead of xhIt forms
It is returned 1) after new winning sub-group；
If fl≤f(xr) ＜ fs, use xrInstead of xhIt is returned 1) after forming new winning sub-group.
3. it shrinks
If fs≤f(xr) ＜ fh, then enable
xp=xc+β(xr-xc), (0 ＜ β ＜ 1) (19)
β is constriction coefficient, generally takes 1/2.
If f (xr)≥fh, then enable
xp=xc+β(xh-xc), (0 ＜ β ＜ 1) (20)
If f (xp) ＜ fh, use xpInstead of xhIt is returned 1) after forming new winning sub-group；
Conversely, enable xi=(xi+xl1))/2, i=0,1 ..., n are returned after forming new winning sub-group.
The winner of new interim sub-group can be obtained by above-mentioned Simplex optimization method.
(4) mind evolutionary optimization radial basis function parameter is improved
Parameter optimization is carried out to radial basis function using mind evolutionary is improved, establishes and improves mind evolutionary optimization
Radial basis neural network carries out parameter photovoltaic power generation power prediction, and Optimization Steps are as follows：
1) realize that solution space to the mapping of space encoder, determines that MEA code lengths are according to the topological structure of RBF
L=L1*L2+L2*L2+L2*L3+L2+L3 (23)
L1For RBF input layer numbers, L2For hidden layer node number, L3For output layer node number.
2) inverse of the mean square error of training set is chosen as each individual and the scoring function of population, and expression formula is
xobs,iRepresent the actual value of i-th of sample, xobs,iRepresent the predicted value of i-th of sample.
3) Population Initialization obtains winning sub-group and interim sub-group, through convergent, operation dissimilation, calculates global optimum
Individual and its score；
4) optimized parameter that IMEA algorithm optimizations RBF is obtained is substituted into RBF to continue to train.
Step 109：The day meteorological data to be measured is input to the improvement mind evolutionary optimization radial direction base nerve
Network model exports the photovoltaic generation power of day to be measured.
In order to verify that photovoltaic generation power provided by the present invention determines the validity of method, sent out with certain Australian photovoltaic
Sample calculation analysis is carried out for power station.
Using on May 1st, 2017 to 30 days 7 June:00~17:00 every the meteorological data of half an hour and photovoltaic generation work(
Rate data as sample data, wherein, May 1 to June 29 be used as history day, June 30 as prediction day.
Photovoltaic generation power of the prediction day per 30min is predicted, in order to verify the effect of optimization of IMEA algorithms, respectively
Establish RBF, heredity-radial basis function (genetic radical basis function algorithm, GA-RBF), particle
Group-radial basis function (particle swarm optimization radical basis function, PSO-RBF) is predicted
Model is compared with the actual value measured by determining method using the present invention, and Fig. 2 is 30 days 4 June provided by the present invention
The comparison diagram of photovoltaic generation power that kind mode obtains, as shown in Figure 2.
4 kinds of prediction model prediction gained photovoltaic generation power curves are walked with actual generation power curve as can be seen from Figure 2
Gesture is basically identical, and the power curve and the deviation of actual power curve that RBF prediction models obtain are apparent compared to other 3 models
Bigger.With root-mean-square error (Root-Mean-Square Error, RMSE) and mean absolute percentage error (Mean
Absolute Percent Error, MAPE) evaluation 4 models prediction effect.By the RMSE corresponding to four kinds of prediction models
It compares with MAPE, it is known that the RBF after GA optimizes, RMSE are reduced to 21.09KW by 30.62KW, and MAPE is by 43.26% drop
As low as 29.57%, the RBF after PSO optimizes, RMSE are reduced to 21.84KW, and MAPE is reduced to 28.35%, and passes through
RBF after the IMEA optimizations prediction effect in four kinds of models is best, and RMSE and MAPE compared to reducing respectively before being not optimised
14.73KW with 20.51%.As the above analysis, RFBNN prediction effects are worst, and GA-RBF, PSO-RBF prediction accuracy are equal
There is promotion, IMEA-RNFNN prediction results are best, therefore the IMEA algorithm optimization RBF parameters based on similar day are effective, energy
Model prediction ability is made to be highly improved.
Following effect can be reached using the determining method of photovoltaic generation power provided by the present invention：
(1) present invention is after each meteorologic factor and photovoltaic generation power related coefficient is calculated, further using average influence
Value-based algorithm carries out the selection of influence factor, more reasonable to the selection of meteorologic factor；
(2) it is similar that the history of prediction day is obtained on the basis of each influence factor weight is considered using optimal Similar operator
Day, make similar day selection algorithm more efficient；
(3) mind evolutionary will be improved for radial base neural net parameter optimization, similar day data and prediction day gas
Image data carries out photovoltaic power generation power prediction as the input for improving mind evolutionary optimization radial basis neural network, carries
The precision of prediction of height prediction photovoltaic generation power, reduces error.
Fig. 3 is the determining system construction drawing of photovoltaic generation power provided by the present invention, as shown in figure 3, a kind of photovoltaic is sent out
The determining system of electrical power, including：
First acquisition module 301, for obtaining history meteorological data and history photovoltaic generation power；The history is meteorological
Data include temperature, humidity, irradiation level, wind speed, wind direction.
Impact factor determining module 302, for according to the history meteorological data and the history photovoltaic generation power
Determine impact factor；The impact factor includes temperature, humidity, irradiation level.
The impact factor determining module 302 specifically includes：Normalized unit, for the history meteorological data
And the history photovoltaic generation power is normalized, the history meteorological data-history photovoltaic generation that obtains that treated
Power relation；The first determination unit of impact factor, for true according to the history meteorological data-history photovoltaic generation power relationship
Determine impact factor.
Weight determination module 303, for determining the weight of the impact factor according to the history photovoltaic generation power.
The weight determination module 303 specifically includes：
Dependency analysis unit, for carrying out correlation point to the impact factor and the history photovoltaic generation power
Analysis, obtains the related coefficient between history photovoltaic generation power and the history meteorological data；
The second determination unit of impact factor, for according to the related coefficient, being determined using average influence value-based algorithm described
Impact factor；
The second determination unit of weight, for determining the weight of the impact factor according to entropy assessment.
Day meteorological data acquisition module 304 to be measured, for obtaining the day meteorological data to be measured of day to be measured；
History day determining module 305, for being determined according to the weight and the similarity of the day meteorological data to be measured is high
In the history day of similarity threshold.
The history day determining module specifically includes：History day determination unit, for according to the weight, using optimal phase
The history day for being higher than similarity threshold with the similarity of the day meteorological data to be measured is determined like Y-factor method Y.
Second acquisition module 306, for obtaining the history day meteorological data and history day photovoltaic generation of the history day
Power.
Optimization module 307 optimizes for the initial weight to radial base neural net and threshold value, after obtaining optimization
Radial base neural net.
The optimization module 307 specifically includes：Initialization process unit, for improving mind evolutionary pair using improvement
The initial weight and threshold value of radial base neural net optimize, the radial base neural net after being optimized.
Model building module 308, for using the history day meteorological data as the radial direction base nerve net after the optimization
The input of network using history day photovoltaic generation power as the output of the radial base neural net after the optimization, is established to improve and be thought
Tie up evolution algorithm optimization radial basis neural network.
Photovoltaic generation power determining module 309, for by the day meteorological data to be measured be input to it is described improvement thinking into
Change algorithm optimization radial basis neural network, export the photovoltaic generation power of day to be measured.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.For system disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related part is said referring to method part
It is bright.
Specific case used herein is expounded the principle of the present invention and embodiment, and above example is said
The bright method and its core concept for being merely used to help understand the present invention；Meanwhile for those of ordinary skill in the art, foundation
The thought of the present invention, in specific embodiments and applications there will be changes.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of determining method of photovoltaic generation power, which is characterized in that including：
Obtain history meteorological data and history photovoltaic generation power；The history meteorological data includes temperature, humidity, irradiation
Degree, wind speed, wind direction；
Impact factor is determined according to the history meteorological data and the history photovoltaic generation power；The impact factor includes
Temperature, humidity, irradiation level；
The weight of the impact factor is determined according to the history photovoltaic generation power；
Obtain the day meteorological data to be measured of day to be measured；
The history day for being higher than similarity threshold with the similarity of the day meteorological data to be measured is determined according to the weight；
Obtain the history day meteorological data and history day photovoltaic generation power of the history day；
The initial weight and threshold value of radial base neural net are optimized, the radial base neural net after being optimized；
Using the history day meteorological data as the input of the radial base neural net after the optimization, with history day photovoltaic generation
Output of the power as the radial base neural net after the optimization establishes and improves mind evolutionary optimization radial direction base nerve net
Network model；
The day meteorological data to be measured is input to the improvement mind evolutionary optimization radial basis neural network, output
The photovoltaic generation power of day to be measured.
2. determining method according to claim 1, which is characterized in that described according to the history meteorological data and the history
Photovoltaic generation power determines impact factor, specifically includes：
The history meteorological data and the history photovoltaic generation power are normalized, the history that obtains that treated
Meteorological data-history photovoltaic generation power relationship；
Impact factor is determined according to the history meteorological data-history photovoltaic generation power relationship.
3. determining method according to claim 1, which is characterized in that described to be determined according to the history photovoltaic generation power
The weight of the impact factor, specifically includes：
Correlation analysis is carried out to the impact factor and the history photovoltaic generation power, obtains history photovoltaic generation power
With the related coefficient between the history meteorological data；
According to the related coefficient, the impact factor is determined using average influence value-based algorithm；
The weight of the impact factor is determined according to entropy assessment.
4. determining method according to claim 3, which is characterized in that described to be determined and the day meteorology to be measured according to the weight
The similarity of data is higher than the history day of similarity threshold, specifically includes：
According to the weight, determine to be higher than similarity with the similarity of the day meteorological data to be measured using optimal Similar operator
The history day of threshold value.
5. determine method according to claim 1, which is characterized in that the initial weight to radial base neural net and
Threshold value optimizes, and the radial base neural net after being optimized specifically includes：
The initial weight and threshold value of radial base neural net are optimized using mind evolutionary is improved, obtained excellent
Radial base neural net after change.
6. a kind of determining system of photovoltaic generation power, which is characterized in that including：
First acquisition module, for obtaining history meteorological data and history photovoltaic generation power；The history meteorological data packet
Include temperature, humidity, irradiation level, wind speed, wind direction；
Impact factor determining module, for determining to influence according to the history meteorological data and the history photovoltaic generation power
The factor；The impact factor includes temperature, humidity, irradiation level；
Weight determination module, for determining the weight of the impact factor according to the history photovoltaic generation power；
Day meteorological data acquisition module to be measured, for obtaining the day meteorological data to be measured of day to be measured；
History day determining module, for according to the weight determine with the similarity of the day meteorological data to be measured be higher than similarity
The history day of threshold value；
Second acquisition module, for obtaining the history day meteorological data and history day photovoltaic generation power of the history day；
Optimization module optimizes the initial weight and threshold value of radial base neural net, the radial direction base god after being optimized
Through network；
Model building module, for using the history day meteorological data as the defeated of the radial base neural net after the optimization
Enter, using history day photovoltaic generation power as the output of the radial base neural net after the optimization, establish and improve mind-evolution
Algorithm optimization radial basis neural network；
Photovoltaic generation power determining module, it is excellent for the day meteorological data to be measured to be input to the improvement mind evolutionary
Change radial basis neural network, export the photovoltaic generation power of day to be measured.
7. determining system according to claim 6, which is characterized in that the impact factor determining module specifically includes：
Normalized unit, for place to be normalized to the history meteorological data and the history photovoltaic generation power
Reason, the history meteorological data-history photovoltaic generation power relationship that obtains that treated；
The first determination unit of impact factor, for determining shadow according to the history meteorological data-history photovoltaic generation power relationship
Ring the factor.
8. determining system according to claim 6, which is characterized in that the weight determination module specifically includes：
Dependency analysis unit, for carrying out correlation analysis to the impact factor and the history photovoltaic generation power,
Obtain the related coefficient between history photovoltaic generation power and the history meteorological data；
The second determination unit of impact factor, for according to the related coefficient, the influence to be determined using average influence value-based algorithm
The factor；
The second determination unit of weight, for determining the weight of the impact factor according to entropy assessment.
9. determining system according to claim 8, which is characterized in that the history day determining module specifically includes：
History day determination unit, for according to the weight, being determined and the day meteorology number to be measured using optimal Similar operator
According to similarity be higher than similarity threshold history day.
10. system is determined according to claim 6, which is characterized in that the optimization module specifically includes：
Optimize unit, for using improve mind evolutionary to the initial weight of radial base neural net and threshold value into
Row optimization, the radial base neural net after being optimized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810001865.8A CN108197744B (en) | 2018-01-02 | 2018-01-02 | Method and system for determining photovoltaic power generation power |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810001865.8A CN108197744B (en) | 2018-01-02 | 2018-01-02 | Method and system for determining photovoltaic power generation power |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108197744A true CN108197744A (en) | 2018-06-22 |
| CN108197744B CN108197744B (en) | 2022-03-08 |
Family
ID=62588079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810001865.8A Active CN108197744B (en) | 2018-01-02 | 2018-01-02 | Method and system for determining photovoltaic power generation power |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197744B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165792A (en) * | 2018-09-14 | 2019-01-08 | 国网天津市电力公司 | A kind of photovoltaic short-term output power prediction technique based on SOA-WNN |
| CN109376863A (en) * | 2018-11-02 | 2019-02-22 | 国网浙江省电力有限公司宁波供电公司 | Photovoltaic power based on MIV-BP neural network is classified prediction technique in short term |
| CN110070226A (en) * | 2019-04-24 | 2019-07-30 | 河海大学 | Photovoltaic power prediction technique and system based on convolutional neural networks and meta learning |
| CN110147908A (en) * | 2019-05-22 | 2019-08-20 | 东莞理工学院 | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm |
| CN110675278A (en) * | 2019-09-18 | 2020-01-10 | 上海电机学院 | Photovoltaic power short-term prediction method based on RBF neural network |
| CN110929953A (en) * | 2019-12-04 | 2020-03-27 | 国网山东省电力公司电力科学研究院 | Photovoltaic power station ultra-short term output prediction method based on cluster analysis |
| CN111260126A (en) * | 2020-01-13 | 2020-06-09 | 燕山大学 | Short-term photovoltaic power generation prediction method considering correlation degree of weather and meteorological factors |
| CN111323847A (en) * | 2018-12-13 | 2020-06-23 | 北京金风慧能技术有限公司 | Method and apparatus for determining weight ratios for analog integration algorithms |
| CN111612648A (en) * | 2020-05-19 | 2020-09-01 | 广东电网有限责任公司电力调度控制中心 | Training method and device of photovoltaic power generation prediction model and computer equipment |
| CN112364477A (en) * | 2020-09-29 | 2021-02-12 | 中国电器科学研究院股份有限公司 | Outdoor empirical prediction model library generation method and system |
| CN113151842A (en) * | 2021-01-29 | 2021-07-23 | 河北建投新能源有限公司 | Method and device for determining conversion efficiency of wind-solar complementary water electrolysis hydrogen production |
| CN113379143A (en) * | 2021-06-23 | 2021-09-10 | 阳光电源股份有限公司 | Typical meteorological year construction method, power generation amount prediction method and related device |
| CN113761023A (en) * | 2021-08-24 | 2021-12-07 | 国网甘肃省电力公司 | Photovoltaic power generation short-term power prediction method based on improved generalized neural network |
| CN116381480A (en) * | 2023-03-30 | 2023-07-04 | 湖南雪墨电气科技有限公司 | Monitoring method, system and medium of intelligent desulfurization, denitrification and dedusting equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700156A (en) * | 2015-01-29 | 2015-06-10 | 广东电网有限责任公司电力科学研究院 | Wind power prediction method for screening variables based on support vector machine |
| CN105469163A (en) * | 2015-12-08 | 2016-04-06 | 国家电网公司 | Similar day selection method used for photovoltaic power station power prediction |
| CN105631517A (en) * | 2015-12-17 | 2016-06-01 | 河海大学 | Photovoltaic power generation power short term prediction method based on mind evolution Elman neural network |
-
2018
- 2018-01-02 CN CN201810001865.8A patent/CN108197744B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700156A (en) * | 2015-01-29 | 2015-06-10 | 广东电网有限责任公司电力科学研究院 | Wind power prediction method for screening variables based on support vector machine |
| CN105469163A (en) * | 2015-12-08 | 2016-04-06 | 国家电网公司 | Similar day selection method used for photovoltaic power station power prediction |
| CN105631517A (en) * | 2015-12-17 | 2016-06-01 | 河海大学 | Photovoltaic power generation power short term prediction method based on mind evolution Elman neural network |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165792A (en) * | 2018-09-14 | 2019-01-08 | 国网天津市电力公司 | A kind of photovoltaic short-term output power prediction technique based on SOA-WNN |
| CN109165792B (en) * | 2018-09-14 | 2021-09-21 | 国网天津市电力公司 | Photovoltaic short-term output power prediction method based on SOA-WNN |
| CN109376863A (en) * | 2018-11-02 | 2019-02-22 | 国网浙江省电力有限公司宁波供电公司 | Photovoltaic power based on MIV-BP neural network is classified prediction technique in short term |
| CN111323847A (en) * | 2018-12-13 | 2020-06-23 | 北京金风慧能技术有限公司 | Method and apparatus for determining weight ratios for analog integration algorithms |
| CN110070226A (en) * | 2019-04-24 | 2019-07-30 | 河海大学 | Photovoltaic power prediction technique and system based on convolutional neural networks and meta learning |
| CN110147908A (en) * | 2019-05-22 | 2019-08-20 | 东莞理工学院 | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm |
| CN110675278A (en) * | 2019-09-18 | 2020-01-10 | 上海电机学院 | Photovoltaic power short-term prediction method based on RBF neural network |
| CN110929953A (en) * | 2019-12-04 | 2020-03-27 | 国网山东省电力公司电力科学研究院 | Photovoltaic power station ultra-short term output prediction method based on cluster analysis |
| CN111260126A (en) * | 2020-01-13 | 2020-06-09 | 燕山大学 | Short-term photovoltaic power generation prediction method considering correlation degree of weather and meteorological factors |
| CN111260126B (en) * | 2020-01-13 | 2022-12-09 | 燕山大学 | Short-term photovoltaic power generation prediction method considering correlation degree of weather and meteorological factors |
| CN111612648A (en) * | 2020-05-19 | 2020-09-01 | 广东电网有限责任公司电力调度控制中心 | Training method and device of photovoltaic power generation prediction model and computer equipment |
| CN111612648B (en) * | 2020-05-19 | 2024-01-19 | 广东电网有限责任公司电力调度控制中心 | Training method and device for photovoltaic power generation prediction model and computer equipment |
| CN112364477A (en) * | 2020-09-29 | 2021-02-12 | 中国电器科学研究院股份有限公司 | Outdoor empirical prediction model library generation method and system |
| CN112364477B (en) * | 2020-09-29 | 2022-12-06 | 中国电器科学研究院股份有限公司 | Outdoor empirical prediction model library generation method and system |
| CN113151842A (en) * | 2021-01-29 | 2021-07-23 | 河北建投新能源有限公司 | Method and device for determining conversion efficiency of wind-solar complementary water electrolysis hydrogen production |
| CN113379143A (en) * | 2021-06-23 | 2021-09-10 | 阳光电源股份有限公司 | Typical meteorological year construction method, power generation amount prediction method and related device |
| CN113761023A (en) * | 2021-08-24 | 2021-12-07 | 国网甘肃省电力公司 | Photovoltaic power generation short-term power prediction method based on improved generalized neural network |
| CN116381480A (en) * | 2023-03-30 | 2023-07-04 | 湖南雪墨电气科技有限公司 | Monitoring method, system and medium of intelligent desulfurization, denitrification and dedusting equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108197744B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197744A (en) | A kind of determining method and system of photovoltaic generation power | |
| 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 | |
| CN104951834A (en) | LSSVM (least squares support vector machine) wind speed forecasting method based on integration of GA (genetic algorithm) and PSO (particle swarm optimization) | |
| CN109657881A (en) | A kind of neural network photovoltaic power generation prediction technique and system suitable for small sample | |
| CN109165764A (en) | A kind of line loss calculation method of genetic algorithm optimization BP neural network | |
| CN104636985B (en) | A kind of transmission line of electricity radio interference Forecasting Methodology of improved BP | |
| CN104978611A (en) | Neural network photovoltaic power generation output prediction method based on grey correlation analysis | |
| CN103683274B (en) | Regional long-term wind power generation capacity probability prediction method | |
| CN105787588B (en) | Dynamic peak-valley time-of-use electricity price method for improving new energy consumption capability | |
| CN107528350B (en) | A kind of wind power output typical scene generation method adapting to long -- term generation expansion planning | |
| CN108280545A (en) | A kind of photovoltaic power prediction technique based on K mean cluster neural network | |
| CN105373857A (en) | Photovoltaic power station irradiance prediction method | |
| CN104463349A (en) | Photovoltaic generated power prediction method based on multi-period comprehensive similar days | |
| CN105678404A (en) | Micro-grid load prediction system and method based on electricity purchased on-line and dynamic correlation factor | |
| CN106650784A (en) | Feature clustering comparison-based power prediction method and device for photovoltaic power station | |
| CN107194495A (en) | A kind of longitudinal Forecasting Methodology of photovoltaic power excavated based on historical data | |
| CN102184337A (en) | Dynamic combination analysis method of new energy generating capacity influenced by meteorological information | |
| CN114970362B (en) | Power grid load scheduling prediction method and system under multi-energy structure | |
| CN105868499B (en) | A kind of electric automobile charging station capacity ratio method containing wind-light storage | |
| Jiang et al. | Comprehensive assessment of wind resources and the low-carbon economy: An empirical study in the Alxa and Xilin Gol Leagues of inner Mongolia, China | |
| CN106130066B (en) | A kind of Multi-objective Robust control method for frequency for independent micro-grid system | |
| CN109978284A (en) | Photovoltaic power generation power time-sharing prediction method based on hybrid neural network model | |
| CN107204615A (en) | A kind of method and system for realizing power prediction | |
| CN106712065B (en) | A kind of charging of electric car is to power distribution network active loss Intrusion Index prediction technique |
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 |