CN105404939A - Short-term power load prediction method - Google Patents
Short-term power load prediction method Download PDFInfo
- Publication number
- CN105404939A CN105404939A CN201510887254.4A CN201510887254A CN105404939A CN 105404939 A CN105404939 A CN 105404939A CN 201510887254 A CN201510887254 A CN 201510887254A CN 105404939 A CN105404939 A CN 105404939A
- Authority
- CN
- China
- Prior art keywords
- load
- short
- white noise
- decomposition
- empirical mode
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 39
- 230000006870 function Effects 0.000 claims abstract description 17
- 238000013277 forecasting method Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 7
- 239000000654 additive Substances 0.000 claims description 3
- 230000000996 additive effect Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 230000000737 periodic effect Effects 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Abstract
The present invention relates to a short-term power load prediction method. The method comprises the following steps: (1), collecting circuit load data of a plurality of days and a plurality of time points in each day, to constitute an original load sequence; (2), performing collective empirical mode decomposition on the original load sequence, and adaptively decomposing the original load sequence into a series of intrinsic mode functions with specific periodic components and a residual amount; (3), using an extreme learning machine to perform prediction on each component obtained through decomposition, and using the extreme learning machine to perform prediction model modeling on load data corresponding to consecutive days and the same time points in each intrinsic mode component and residual component; and (4), performing power load prediction by using the obtained prediction model. According to the short-term power load prediction method, the problem of an end effect of traditional empirical mode decomposition is overcome. On the other hand, a generalization ability and a calculation speed of the extreme learning machine are better than those of an artificial neural network method that is commonly used at present.
Description
Technical field
The present invention relates to a kind of Short-Term Load Forecasting Method, a kind of Short-Term Load Forecasting Method based on gathering empirical mode decomposition and extreme learning machine is specifically set.
Background technology
Short-term load forecasting is a research emphasis in Load Prediction In Power Systems research.The precision of short-term load forecasting directly has influence on power system security economic stability and runs, and is significant to realizing electrical network scientific management.In recent years, load prediction technology achieves considerable progress already, and Forecasting Methodology develops into modern artificial intelligence forecasting techniques from classic method, and the precision of prediction of load have also been obtained suitable raising.But along with the development of China's Urbanization Construction, user power utilization demand will increase further, simultaneously also for the scale access of renewable distributed power source provides enforceable external environment condition.To become based on the user side micro-capacitance sensor of residential quarter, business premises, industrial working and promote that regenerative resource on-site elimination utilizes, play the effective means of distributed electrical source efficiency.Short-term load forecasting is the important component part of user side microgrid energy management system, is the basis realizing micro-capacitance sensor Optimized Operation, predicts the outcome and will directly affect micro-capacitance sensor operation reserve and power trade.Correlative study shows, higher micro-grid load predicated error will cause operating cost significantly to increase.Therefore, current short-term load forecasting method can not meet the demand of intelligent micro-grid completely.
Current load forecasting method mainly comprises routine techniques and artificial intelligence approach, and the principle of conventional forecasting techniques is fairly simple and relatively easily realize, but these methods lack the ability setting up comprehensively the forecast model of accurate description load variations feature uniformly.Compared with the Forecasting Methodology of routine, Intelligentized method has very large advantage and potential in the unified rational load forecasting model of foundation.But the Wavelet transformation method of current extensive employing can not select suitable morther wavelet and decomposition scale according to the concrete feature of load sample data own, is difficult to obtain gratifying decomposition result and precision of prediction.On the other hand, in Forecasting Methodology, there is the problem of over-fitting and locally optimal solution in the Artificial Neural Network of current extensive employing.
Summary of the invention
The object of this invention is to provide a kind of Short-Term Load Forecasting Method, there is the problem of certain defect in order to solve existing load forecasting method all separately.
For achieving the above object, the solution of the present invention comprises a kind of Short-Term Load Forecasting Method, comprises the following steps:
(1), gather the circuit load data of some skies and several time points in every day, form original loads sequence;
(2), to described original loads sequence carry out set empirical mode decomposition, original loads sequence self-adapting is decomposed into intrinsic mode function and a residual volume of a series of specific period composition;
(3), for each decompose the component obtained, adopt extreme learning machine to predict respectively; Limit of utilization learning machine carries out forecast model modeling respectively for Consecutive Days, load data corresponding in the same time mutually in each intrinsic modal components and residual components, utilizes the forecast model obtained to carry out the prediction of electric load;
(4), by linear superposition process, provide and finally predict the outcome.
Described set empirical mode decomposition is carried out to original loads sequence before, Bad data processing is carried out to original loads sequence.
Described step (2) specifically comprises the following steps:
1), the execution number of times M of initialization entirety repetition;
2), at original loads sequence x (t) upper interpolation white noise n
it () obtains new signal x
it (), computing formula is: x
i(t)=x (t)+n
i(t),
Wherein, this white noise is obeyed (0, (α σ)
2) normal distribution, the standard deviation that σ=std (x (t)) is signal, α is the intensive parameter of additive white noise, here n
it () is i-th white noise added, x
it () is the new signal obtained after adding white noise i-th time, i=1,2 ..., M;
3), adopt empirical mode decomposition method to newly-generated signal x
it () is carried out decomposition and is obtained a series of intrinsic mode function, computing formula is:
Wherein, S is the number of decomposing the intrinsic mode function obtained through empirical mode decomposition method, r
i,St () is residual volume, c
i,st () adds s the intrinsic mode function obtained after the signal that obtains of white noise carries out empirical mode decomposition, s=1,2 to i-th time ..., S, i=1,2 ..., M;
4) set of following intrinsic mode function, is obtained:
Describedly to the step that original loads sequence carries out Bad data processing be:
1), rejecting abnormalities data, carry out the level and smooth of data;
2), data are normalized.
In Short-Term Load Forecasting Method provided by the invention, the set empirical mode decomposition adopted can adaptive be a series of intrinsic modal components by the load Series Decomposition through Bad data processing, and overcome the end effect problem of Conventional wisdom mode decomposition.On the other hand, the generalization ability of extreme learning machine and computing velocity are better than the current Artificial Neural Network generally adopted.
Accompanying drawing explanation
Fig. 1 is Short-Term Load Forecasting Method process flow diagram;
Fig. 2 is the process flow diagram carrying out gathering empirical mode decomposition to original loads sequence;
Fig. 3 is the result schematic diagram that beginning load sequence carries out gathering empirical mode decomposition;
Fig. 4 is the comparison chart predicting load curve and realized load curve certain working day.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described in detail.
Do not invent and a kind of Short-Term Load Forecasting Method be provided, as shown in Figure 1, comprise the following steps:
(1), gather the circuit load data of some skies and several time points in every day, form original loads sequence, and Bad data processing is carried out to original loads sequence.
(2), to described original loads sequence carry out set empirical mode decomposition, original loads sequence self-adapting is decomposed into intrinsic mode function and a residual volume of a series of specific period composition;
As shown in Figure 2, this step specifically comprise for:
1), the execution number of times M of initialization entirety repetition;
2), at original loads sequence x (t) upper interpolation white noise n
it () obtains new signal x
it (), computing formula is: x
i(t)=x (t)+n
i(t),
Wherein, this white noise is obeyed (0, (α σ)
2) normal distribution, the standard deviation that σ=std (x (t)) is signal, α is the intensive parameter of additive white noise, here n
it () is i-th white noise added, x
it () is the new signal obtained after adding white noise i-th time, i=1,2 ..., M;
3), adopt empirical mode decomposition method to newly-generated signal x
it () is carried out decomposition and is obtained a series of intrinsic mode function, computing formula is:
Wherein, S is the number of decomposing the intrinsic mode function obtained through empirical mode decomposition method, r
i,St () is residual volume, c
i,st () adds s the intrinsic mode function obtained after the signal that obtains of white noise carries out empirical mode decomposition, s=1,2 to i-th time ..., S, i=1,2 ..., M;
4) set of following intrinsic mode function, is obtained:
(3), for each decompose the component obtained, adopt extreme learning machine to predict respectively; Limit of utilization learning machine carries out forecast model modeling respectively for Consecutive Days, load data corresponding in the same time mutually in each intrinsic modal components and residual components.Concrete process can be used for doing the process returned with reference to extreme learning machine, because extreme learning machine belongs to the common practise of this area, so, repeat no more here.
(4), the forecast model obtained is utilized to carry out the prediction of electric load.
(5) by linear superposition process, provide and finally predict the outcome.
In above-mentioned steps (2), the object of interpolation white noise is the end effect problem in order to eliminate empirical mode decomposition (EMD).Due to when applying EMD method during the appearance of end effect, in screening process each time, the local mean values of signal to be calculated according to the upper lower envelope of signal; Upper lower envelope is provided by 3 Based on Interpolating Splines by the local maximum of signal and minimal value.Because signal two ends can not be in maximum value and minimal value simultaneously, therefore, upper lower envelope inevitably there will be Divergent Phenomenon at the two ends of data-signal, and this Divergent Phenomenon is just called end effect.Occur that end effect makes the result of decomposing no longer have actual physical significance, do not wished to see.
In signal to be decomposed, add the white noise of zero-mean, after EMD decomposes, equally distributed each frequency component that signal can be made to comprise is come by the decomposition of regularity.For white noise, EMD decomposition is similar to an effective scale-of-two wave filter, and except first IMF, the power spectrum of remaining IMF all presents similar bandpass characteristics.
EMD side's ratio juris is in original signal, add several times white noise, using the to be decomposed signal of the combination of signal and noise as a signal, utilize the uniform distribution properties of white noise spectrum, when signal loading spreads all in the white noise background that whole time frequency space distributes consistent, the signal of different scale can be distributed on suitable reference yardstick automatically, and due to the characteristic of zero mean noise, then carry out EMD process respectively, be finally averaging the true mode obtaining approaching.
In addition, if load sample data are a point per hour, then the Number of Models that each component is corresponding is 24, time t is substituted into respectively forecast model and can obtain the predicted load of each component at each corresponding time point.Wherein, each intrinsic modal components represents a model; Same intrinsic mode component Model to not on the same day, i.e. intrinsic mode component Model representative not synchronization on the same day.Suppose that n days (24 time points) then can have n bar load curve, when investigating a certain particular moment of this n days, during the load characteristic at such as 8 o'clock of morning, then can obtain the data of the not same intrinsic modal components on the same day corresponding to 8 o'clock, therefore, for within one day 24 hours, then there being 24 such data, be 24 from the Number of Models corresponding to each component this angle.
Application example:
The history Power system load data choosing China certain city year 7 to Dec 19 Dec is as example, and with Dec 7 to Dec 17 for input data, data were set up extreme learning machine forecast model carry out network training for being exported data Dec 18; With Dec 8 to Dec 18 data for input data, 24 periods on Dec 19 are predicted.
Forecasting process carries out according to flow process shown in Fig. 1.After Bad data processing is carried out to input load sequence, carry out set empirical mode decomposition EMD, obtain a series of steady intrinsic modal components IMF with single mode; Predicted respectively each component by extreme learning machine ELM, then reconstruct provides and finally predicts the outcome again.Wherein gather the performing step of empirical mode decomposition as shown in Figure 2.
Fig. 3 is the result adopting set empirical mode decomposition to decompose the load sequence of above-mentioned 13 days.Load sequence is a kind of typical periodicity and randomness and the non-stationary signal deposited, and set empirical mode decomposition can will be a series of intrinsic modal components according to frequency sequential breakdown from high in the end with giving constant load sequence self-adapting.
In Fig. 3, a is original signal, and b ~ h is 7 IMF components that set empirical mode decomposition obtains, and i is surplus.As can be seen from the figure, b is the random component of high frequency, without any rule, is the random component part of original series; C and d has certain periodicity, is original series periodic component; All the other components have obvious trend feature, are the trend component of original series.From the angle of part throttle characteristics, the load of any time can be made up of random component, weather sensitive load and normal component, the characteristic division of this load that these three kinds of components that load sequence obtains after set empirical mode decomposition are just in time corresponding in a sense.
Adopt the inventive method to predict the outcome as shown in Figure 4, as can be seen from the figure, adopt institute's extracting method more adequately to predict the load of prediction day.
As mentioned above, first the method adopts set empirical mode decomposition to be a series of unifrequent intrinsic mode functions by load Series Decomposition, wherein contains the high frequency random element of original series, periodic component and normal trend components.Then adopt extreme learning machine to set up forecast model respectively to each component, finally reconstruct is finally predicted the outcome.The method proposed is that power-system short-term load forecasting provides a kind of new approaches.
Be presented above concrete embodiment, but the present invention is not limited to described embodiment.Basic ideas of the present invention are above-mentioned basic scheme, and for those of ordinary skill in the art, according to instruction of the present invention, designing the model of various distortion, formula, parameter does not need to spend creative work.The change carried out embodiment without departing from the principles and spirit of the present invention, amendment, replacement and modification still fall within the scope of protection of the present invention.
Claims (4)
1. a Short-Term Load Forecasting Method, is characterized in that, comprises the following steps:
(1), gather the circuit load data of some skies and several time points in every day, form original loads sequence;
(2), to described original loads sequence carry out set empirical mode decomposition, original loads sequence self-adapting is decomposed into intrinsic mode function and a residual volume of a series of specific period composition;
(3), for each decompose the component obtained, adopt extreme learning machine to predict respectively; Limit of utilization learning machine carries out forecast model modeling respectively for Consecutive Days, load data corresponding in the same time mutually in each intrinsic modal components and residual components, utilizes the forecast model obtained to carry out the prediction of electric load;
(4), by linear superposition process, provide and finally predict the outcome.
2. Short-Term Load Forecasting Method according to claim 1, is characterized in that, described set empirical mode decomposition is carried out to original loads sequence before, Bad data processing is carried out to original loads sequence.
3. Short-Term Load Forecasting Method according to claim 1, is characterized in that, described step (2) specifically comprises the following steps:
1), the execution number of times M of initialization entirety repetition;
2), at original loads sequence x (t) upper interpolation white noise n
it () obtains new signal x
it (), computing formula is: x
i(t)=x (t)+n
i(t),
Wherein, this white noise is obeyed (0, (α σ)
2) normal distribution, the standard deviation that σ=std (x (t)) is signal, α is the intensive parameter of additive white noise, here n
it () is i-th white noise added, x
it () is the new signal obtained after adding white noise i-th time, i=1,2 ..., M;
3), adopt empirical mode decomposition method to newly-generated signal x
it () is carried out decomposition and is obtained a series of intrinsic mode function, computing formula is:
Wherein, S is the number of decomposing the intrinsic mode function obtained through empirical mode decomposition method, r
i,St () is residual volume, c
i,st () adds s the intrinsic mode function obtained after the signal that obtains of white noise carries out empirical mode decomposition, s=1,2 to i-th time ..., S, i=1,2 ..., M;
4) set of following intrinsic mode function, is obtained:
4. Short-Term Load Forecasting Method according to claim 2, is characterized in that, describedly to the step that original loads sequence carries out Bad data processing is:
1), rejecting abnormalities data, carry out the level and smooth of data;
2), data are normalized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510887254.4A CN105404939A (en) | 2015-12-04 | 2015-12-04 | Short-term power load prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510887254.4A CN105404939A (en) | 2015-12-04 | 2015-12-04 | Short-term power load prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105404939A true CN105404939A (en) | 2016-03-16 |
Family
ID=55470412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510887254.4A Pending CN105404939A (en) | 2015-12-04 | 2015-12-04 | Short-term power load prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105404939A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106208388A (en) * | 2016-08-31 | 2016-12-07 | 科大智能电气技术有限公司 | A kind of intelligence charging system and short term basis load prediction implementation method thereof in order |
| CN106529680A (en) * | 2016-10-27 | 2017-03-22 | 天津工业大学 | Multiscale extreme learning machine integrated modeling method based on empirical mode decomposition |
| CN106788064A (en) * | 2017-03-10 | 2017-05-31 | 南京理工大学 | Induction motor stator resistance parameter identification method based on EMD ELM |
| CN108256676A (en) * | 2017-12-29 | 2018-07-06 | 国网江苏省电力有限公司检修分公司 | A kind of Methods of electric load forecasting of meter and load fluctuation asymmetrical characteristic |
| CN108303652A (en) * | 2018-01-18 | 2018-07-20 | 武汉理工大学 | A kind of lithium battery method for predicting residual useful life |
| CN109461091A (en) * | 2018-05-25 | 2019-03-12 | 中国农业大学 | Consider the Calculation of electric charge method and information system of photovoltaic and refrigeration duty correlation |
| CN109886498A (en) * | 2019-03-01 | 2019-06-14 | 北京邮电大学 | A kind of EMD-GRU Short-Term Load Forecasting Method based on feature selecting |
| CN110264001A (en) * | 2019-06-20 | 2019-09-20 | 国网上海市电力公司 | Electro-load forecast method based on multiple timings |
| CN110633844A (en) * | 2019-08-25 | 2019-12-31 | 天津大学 | Building energy system simulation prediction method based on EMD and ANN and application |
| CN111105321A (en) * | 2019-12-03 | 2020-05-05 | 湘潭大学 | Power load prediction method based on EEMD secondary decomposition |
| CN111126659A (en) * | 2019-11-18 | 2020-05-08 | 国网安徽省电力有限公司六安供电公司 | Power load prediction method and system |
| CN111160625A (en) * | 2019-12-10 | 2020-05-15 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN111507505A (en) * | 2020-03-20 | 2020-08-07 | 苏州丰华声赫智能科技有限公司 | Method for constructing reservoir daily input prediction model |
| CN111539558A (en) * | 2020-04-03 | 2020-08-14 | 东南大学 | Power load prediction method adopting optimized extreme learning machine |
| CN111555329A (en) * | 2020-06-05 | 2020-08-18 | 西安石油大学 | Energy storage capacity configuration method for autonomous micro-grid |
| CN111861553A (en) * | 2020-07-14 | 2020-10-30 | 河南农业大学 | Agricultural product price prediction method based on EMD-ELM |
| CN112232600A (en) * | 2020-11-17 | 2021-01-15 | 烟台海颐软件股份有限公司 | Short-term power load prediction method and system based on variational modal decomposition |
| CN113837441A (en) * | 2021-08-24 | 2021-12-24 | 山东大学 | Power load prediction method and system considering reconstruction accuracy after EEMD decomposition |
-
2015
- 2015-12-04 CN CN201510887254.4A patent/CN105404939A/en active Pending
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106208388A (en) * | 2016-08-31 | 2016-12-07 | 科大智能电气技术有限公司 | A kind of intelligence charging system and short term basis load prediction implementation method thereof in order |
| CN106529680A (en) * | 2016-10-27 | 2017-03-22 | 天津工业大学 | Multiscale extreme learning machine integrated modeling method based on empirical mode decomposition |
| CN106529680B (en) * | 2016-10-27 | 2019-01-29 | 天津工业大学 | A kind of multiple dimensioned extreme learning machine integrated modelling approach based on empirical mode decomposition |
| CN106788064A (en) * | 2017-03-10 | 2017-05-31 | 南京理工大学 | Induction motor stator resistance parameter identification method based on EMD ELM |
| CN108256676A (en) * | 2017-12-29 | 2018-07-06 | 国网江苏省电力有限公司检修分公司 | A kind of Methods of electric load forecasting of meter and load fluctuation asymmetrical characteristic |
| CN108256676B (en) * | 2017-12-29 | 2021-11-16 | 国网江苏省电力有限公司检修分公司 | Power load prediction method considering load fluctuation asymmetry characteristic |
| CN108303652A (en) * | 2018-01-18 | 2018-07-20 | 武汉理工大学 | A kind of lithium battery method for predicting residual useful life |
| CN109461091A (en) * | 2018-05-25 | 2019-03-12 | 中国农业大学 | Consider the Calculation of electric charge method and information system of photovoltaic and refrigeration duty correlation |
| CN109461091B (en) * | 2018-05-25 | 2020-08-28 | 中国农业大学 | Power utilization load calculation method considering correlation between photovoltaic load and cold load and information system |
| CN109886498A (en) * | 2019-03-01 | 2019-06-14 | 北京邮电大学 | A kind of EMD-GRU Short-Term Load Forecasting Method based on feature selecting |
| CN110264001A (en) * | 2019-06-20 | 2019-09-20 | 国网上海市电力公司 | Electro-load forecast method based on multiple timings |
| CN110633844A (en) * | 2019-08-25 | 2019-12-31 | 天津大学 | Building energy system simulation prediction method based on EMD and ANN and application |
| CN110633844B (en) * | 2019-08-25 | 2023-02-24 | 天津大学 | Building energy system simulation prediction method based on EMD and ANN and application |
| CN111126659A (en) * | 2019-11-18 | 2020-05-08 | 国网安徽省电力有限公司六安供电公司 | Power load prediction method and system |
| CN111105321A (en) * | 2019-12-03 | 2020-05-05 | 湘潭大学 | Power load prediction method based on EEMD secondary decomposition |
| CN111160625A (en) * | 2019-12-10 | 2020-05-15 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN111160625B (en) * | 2019-12-10 | 2020-10-27 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN111507505A (en) * | 2020-03-20 | 2020-08-07 | 苏州丰华声赫智能科技有限公司 | Method for constructing reservoir daily input prediction model |
| CN111539558A (en) * | 2020-04-03 | 2020-08-14 | 东南大学 | Power load prediction method adopting optimized extreme learning machine |
| CN111539558B (en) * | 2020-04-03 | 2023-05-16 | 东南大学 | Power load prediction method adopting optimization extreme learning machine |
| CN111555329A (en) * | 2020-06-05 | 2020-08-18 | 西安石油大学 | Energy storage capacity configuration method for autonomous micro-grid |
| CN111555329B (en) * | 2020-06-05 | 2022-01-28 | 西安石油大学 | Energy storage capacity configuration method for autonomous micro-grid |
| CN111861553A (en) * | 2020-07-14 | 2020-10-30 | 河南农业大学 | Agricultural product price prediction method based on EMD-ELM |
| CN112232600A (en) * | 2020-11-17 | 2021-01-15 | 烟台海颐软件股份有限公司 | Short-term power load prediction method and system based on variational modal decomposition |
| CN113837441A (en) * | 2021-08-24 | 2021-12-24 | 山东大学 | Power load prediction method and system considering reconstruction accuracy after EEMD decomposition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105404939A (en) | Short-term power load prediction method | |
| CN108256697B (en) | Prediction method for short-term load of power system | |
| Huang et al. | Forecasting hourly solar irradiance using hybrid wavelet transformation and Elman model in smart grid | |
| CN105184391B (en) | Wind farm wind velocity and power forecasting method based on wavelet decomposition and support vector machines | |
| CN109063939B (en) | Wind speed prediction method and system based on neighborhood gate short-term memory network | |
| CN111832809B (en) | Building energy consumption load prediction method and system based on Holt-Winters and extreme learning machine | |
| CN106951990A (en) | Electric load intelligent Forecasting and device | |
| Wang et al. | A novel wind speed forecasting method based on ensemble empirical mode decomposition and GA-BP neural network | |
| Zhang et al. | Load prediction based on hybrid model of VMD-mRMR-BPNN-LSSVM | |
| Plakhotnikov et al. | The Use of Artificial Intelligence in Cyber-Physical Systems | |
| CN107563573B (en) | Solar power generation capacity prediction method based on self-adaptive learning hybrid model | |
| Qin et al. | Forecasting of China consumer price index based on EEMD and SVR method | |
| CN116011226A (en) | Method and system for predicting long-period dynamic current-carrying capacity of exposed cable | |
| CN105528517A (en) | Photovoltaic power station power prediction method and system on basis of neural network and wavelet decomposition | |
| Dongyang et al. | Wind speed time series forecasting method in wind farm based on EEMD | |
| CN114925940A (en) | Holiday load prediction method and system based on load decomposition | |
| CN113139698A (en) | Load prediction method, device and equipment | |
| Zhang et al. | Power Load Forecasting Model Based on LSTM and Prophet algorithm | |
| Liu et al. | Ultra-short-term forecasting method of wind power based on W-BiLSTM | |
| Zhang et al. | Short-term power load forecasting model design based on EMD-PSO-GRU | |
| Zhou et al. | Combined voltage forecasting method based on EMD-CNN for distribution networks with distributed PVs | |
| Gu et al. | Wind power prediction based on VMD-neural network | |
| Wang et al. | Ultra-short-term wind speed forecasting based on meta learning with signal trend and fluctuation decomposition | |
| Dong et al. | An integrated ultra short term power forecasting method for regional wind–pv–hydro | |
| Han et al. | Short-term prediction of wind power combining GM (1, 1) model with cloud model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160316 |