CN111539564A - Daily runoff time sequence prediction method based on ESMD and NNBR - Google Patents
Daily runoff time sequence prediction method based on ESMD and NNBR Download PDFInfo
- Publication number
- CN111539564A CN111539564A CN202010304163.4A CN202010304163A CN111539564A CN 111539564 A CN111539564 A CN 111539564A CN 202010304163 A CN202010304163 A CN 202010304163A CN 111539564 A CN111539564 A CN 111539564A
- Authority
- CN
- China
- Prior art keywords
- daily runoff
- daily
- esmd
- nnbr
- sequence
- 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 40
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 238000005259 measurement Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000010248 power generation Methods 0.000 abstract description 3
- 230000004907 flux Effects 0.000 abstract 1
- 239000013598 vector Substances 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Analysis (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Optimization (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Computational Mathematics (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a daily runoff time series prediction method based on ESMD and NNBR, which comprises the following steps: s1, collecting historical actual measurement daily runoff time sequence data, and decomposing the historical actual measurement daily runoff sequence to obtain a subsequence and a daily runoff sequence decomposition residual error; s2, establishing NNBRs for the decomposed subsequences, and predicting the daily flux through the NNBRs; s3, reconstructing the daily runoff flow prediction result and the daily runoff sequence decomposition residual error of each subsequence through an ESMD algorithm to obtain a daily runoff prediction sequence. The method combines NNBR and ESMD, and decomposes, predicts and reconstructs different components forming the hydrological process, so that the prediction precision of the daily runoff time sequence is effectively improved compared with a single NNBR model, the reservoir scheduling operation mode and the hydropower station power generation plan can be optimized according to the daily runoff time sequence, and the working energy efficiency of the reservoir hydropower station is improved.
Description
Technical Field
The invention relates to the technical field of runoff prediction, in particular to a daily runoff time series prediction method based on ESMD and NNBR.
Background
The runoff prediction has important significance for the operation management of a reservoir hydropower station, is an important basis for correctly making an optimal scheduling operation mode of the reservoir and a power generation plan of the hydropower station, and directly influences the operation mode and the working energy efficiency of the reservoir. For the short-term runoff forecasting, due to the influences of comprehensive factors such as climate, basin underlying surface conditions, human activities and the like, the daily runoff shows stronger characteristics such as nonlinearity, variability and multi-scale, so that the forecasting difficulty of the daily runoff is increased. At present, methods adopted for runoff forecasting at home and abroad mainly comprise a cause analysis method, a statistical analysis method, a gray system method, a fuzzy algorithm, an artificial neural network, wavelet analysis, a combination of the methods and the like. Due to the factors of all aspects such as basin conditions, various models have advantages, disadvantages and applicable conditions.
Therefore, a method for accurately predicting the radial flow under various watershed conditions is needed.
Disclosure of Invention
The invention aims to provide a daily runoff time sequence prediction method based on ESMD and NNBR, which aims to solve the problems in the prior art and effectively improve the prediction precision of the daily runoff time sequence.
In order to achieve the purpose, the invention provides the following scheme: the invention provides a daily runoff time series prediction method based on ESMD and NNBR, which comprises the following steps:
s1, collecting historical actual measurement daily runoff time sequence data, decomposing the historical actual measurement daily runoff sequence by using an extreme point symmetric model decomposition (ESMD) to obtain a subsequence and a daily runoff sequence decomposition residual error;
s2, establishing a nearest neighbor sampling regression model NNBR for the subsequences obtained by decomposition in the step S1, and predicting each subsequence through the NNBR;
and S3, reconstructing the prediction result of each subsequence in the step S2 and the daily runoff sequence decomposition residual error obtained in the step S1 through an ESMD algorithm to obtain a prediction sequence of daily runoff.
Preferably, the daily runoff time series prediction method based on the ESMD and the NNBR further comprises the precision calculation of the daily runoff prediction result.
Preferably, the accuracy calculation index of the daily runoff prediction result comprises: relative error, average relative error level, deterministic coefficient, process yield.
Preferably, the specific method for decomposing the historical measured daily runoff sequence by using the ESMD in step S1 includes:
s1.1, calculating all extreme points in daily runoff time sequence data, wherein the extreme points comprise a maximum point and a minimum point;
s1.2, sequentially connecting all adjacent extreme points, and marking the middle point of a connecting line between the adjacent extreme points;
s1.3, respectively adding middle points of left and right boundaries of the extreme points by a linear difference method;
s1.4, constructing a plurality of interpolation curves by using the midpoints of connecting lines between adjacent extreme points and the midpoints of left and right boundaries;
s1.5, repeating the steps S1.1-S1.4 to carry out iterative computation on the average value of the interpolation curve to obtain a first subsequence of daily runoff time sequence data Y;
s1.6, repeating the steps S1.1-S1.5 to carry out iterative computation on the subsequence of the daily runoff time sequence data until the residual error does not exceed any extreme point in the daily runoff time sequence data, and obtaining the decomposition residual error of the daily runoff time sequence data;
s1.7, setting an integer interval, changing the iteration times on the integer interval, repeating the steps S1.1-S1.6, and calculating the variance sigma of the residual error2And making sigma/sigma0Graph against number of iterations, where σ0Is dayStandard deviation of runoff time series data;
s1.8, passage σ/σ0Obtaining a relation graph with the iteration times to obtain sigma/sigma0And (4) taking the value of the corresponding iteration times when the value is the minimum value, and repeating the steps from S1.1 to S1.6 to obtain the daily runoff sequence decomposition residual error.
The invention discloses the following technical effects:
the method combines NNBR and ESMD, and decomposes, predicts and reconstructs different components forming the hydrological process, so that the prediction precision of the daily runoff time sequence is effectively improved compared with a single NNBR model, the reservoir scheduling operation mode and the hydropower station power generation plan can be optimized according to the daily runoff time sequence, and the working energy efficiency of the reservoir hydropower station is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a daily runoff time series prediction method based on ESMD and NNBR of the present invention;
FIG. 2 shows an ESMD-based decomposition result according to an embodiment of the present invention;
FIG. 3 shows the result of the daily runoff prediction of a Model1-Model12 according to an embodiment of the present invention;
fig. 4 is a comparison result of the measured value and the predicted value of the daily runoff in the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, the invention provides a daily runoff time series prediction method based on ESMD and NNBR, which includes the following steps:
s1, collecting historical actual measurement daily runoff time sequence data Y ═ x1,x2,…,xnAnd decomposing the historical actual measurement daily runoff sequence by using an ESMD (Extreme-point Symmetric Mode Decomposition) to obtain a subsequence and a daily runoff sequence Decomposition residual error.
The extreme point symmetric mode decomposition ESMD can decompose nonlinear time series signals to obtain amplitudes and frequencies of different modes, and can identify hydrological process composition of time series.
The specific method for decomposing the historical actual measurement daily runoff sequence by using the ESMD comprises the following steps:
s1.1, calculating all extreme points S in daily runoff time sequence data YiI is more than or equal to 1 and less than or equal to n, wherein the extreme points comprise maximum points and minimum points;
s1.2, connecting all adjacent extreme points S in sequenceiAnd use of F in combinationiMarking the middle point of a connecting line between adjacent extreme points, wherein i is more than or equal to 1 and less than or equal to n;
s1.3, respectively adding middle points F of left and right boundaries of extreme points by a linear interpolation method0And Fn;
S1.4, constructing p interpolation curves L by using the obtained n +1 middle points1,…,Lp(p is not less than 1), and the average value L of the interpolation curve is (L)1+…+Lp)/p。
S1.5, repeating the steps S1.1-S1.4 to carry out iterative calculation on the average value of the interpolation curve, and when the absolute value L is equal to*If the absolute value is less than or equal to the allowable error, or the iteration time reaches a preset maximum iteration time K, obtaining a first subsequence Model1 of the daily runoff time sequence data Y;
s1.6, repeating the steps S1.1-S1.5 to carry out iterative computation on the subsequence of the daily runoff time sequence data Y until the residual error R does not exceed any extreme point in the daily runoff time sequence data Y, so as to obtain a decomposition residual error R of the daily runoff time sequence data Y;
s1.7, setting an integer interval [ Kmin,Kmax]In the integer interval [ Kmin,Kmax]Changing the maximum iteration number K, repeating the steps S1.1-S1.6 to obtain a residual R, and calculating the variance sigma of the residual R2And making sigma/sigma0Graph of relation to K, where σ0Is the standard deviation of daily runoff time series data Y;
S1.8、σ/σ0taking the corresponding K value when the minimum value is taken as K0,K0∈[Kmin,Kmax]Is a reaction of K0Substituting the step S1.5, and repeating the steps S1.1-S1.6 to obtain a daily runoff sequence decomposition residual error which is marked as R0Sequential decomposition residual R of daily runoff0An optimal AGM (adaptive global mean) curve is obtained.
S2, for the subsequences obtained by decomposition in the step S1, NNBRs (nearest neighbor sampling regression models) are established, and prediction of each subsequence is carried out through the NNBRs.
The nearest neighbor sampling regression model NNBR avoids making certain assumption on the dependent form and the probability distribution form of a research object, is a nonparametric model based on data driving and without identifying parameters, and has the basic idea that: there is a certain relation between the occurrence and development of the objective world, and the future motion trail has similarity with the history, i.e. the future development pattern can be searched from the known numerous patterns.
The specific method for predicting the daily runoff through the NNBR comprises the following steps:
known subsequence { Xt}nWherein X istDependent on the previous P neighbouring history values Xt-1,Xt-2,…,Xt-pDefining a feature vector Dt=(Xt-1,Xt-2,…Xt-p),XtIs DtIs based on the current feature vector D, based on the subsequent values of (t ═ P +1, P +2, … n)i=(Xi-1,Xi-2,…Xi-p),i∈[1,P]To predict DiSubsequent value X ofi。
In the feature vector Dt=(Xt-1,Xt-2,…Xt-p) In the method, K nearest neighbor feature vectors are selected and recorded as D1(i),D2(i),…,DK(i),K∈[1,t]The corresponding subsequent values are X respectively1(i),X2(i),…,XK(i)(ii) a Wherein the nearest neighbor passes through DiAnd DtThe Euclidean distance between the two is judged, the smaller the distance is, DiAnd DtThe closer to the nearest neighbor, the Euclidean distance is calculated as shown in formula (1), and K nearest neighbor feature vectors D1(i),D2(i),…,DK(i)And DiThe Euclidean distance between them is marked as R1(i),R2(i),…,RK(i);
Wherein R ist(i)Represents DiAnd DtThe Euclidean distance between; dij,dtjAre respectively Di,DtThe jth element of (1).
Rj(i)The smaller, thej(i)And DiThe more adjacent, then Xi=Xj(i)Possibility of (2) Wj(i)The larger (j ═ 1,2, …, K); that is, Xj(i)To XiThe greater the contribution of (c); wherein, the handle Wj(i)Represents Xj(i)Sampling weight of, see Wj(i)Distance from Euclidean Rj(i)In inverse proportion.
The single subsequence NNBR is represented by formula (2):
s3, by ESMDThe algorithm predicts the result of each subsequence in step S2 and the residual R obtained in step S10And reconstructing to obtain a prediction sequence of daily runoff.
S4, calculating the precision of the daily runoff prediction result; calculating the accuracy of the daily runoff prediction result through the following indexes:
1) relative error;
the specific calculation method of the relative error is shown as the formula (3):
2) average relative error levels;
the average relative error level of multiple predictions is represented by averaging the absolute values of the relative errors.
3) A certainty coefficient;
according to the hydrological information specification, the certainty coefficient DC is the degree of coincidence between the prediction process and the actual measurement process, as shown in equation (4):
wherein, y0(i) Is an actual measurement value; y isc(i) Is a predicted value;is the mean value of measured values; n is the sequence length.
4) The process qualification rate;
when the predicted error is smaller than the allowable error, the prediction is qualified; the percentage of the ratio of the number of qualified predictions to the total number of predictions is the process yield, which represents the overall accuracy level of the multiple predictions, as shown in equation (5):
wherein QR is the process qualification rate; n is the qualified prediction times; and m is the total prediction times.
The first embodiment is as follows:
obtaining a measured daily runoff time sequence { x (i) in 41 years in 1960-2001 of the Hua county station in Wei river basin; and i is 1,2, … n, 28 days are taken in 2 months every year, 365 days are counted every year, and the data of the 2001-year daily runoff is predicted by adopting 1960-2000 actual measurement daily runoff time sequence data for model calibration.
First, the time series data of the actual daily runoff in 1960-.
Secondly, NNBRs are respectively established for Model1, models 2, … and Model12 subsequences, the feature vector dimension p is taken as 3, and the nearest neighbor number K is taken asAnnual daily runoff in 2001 was predicted by NNBR.
In the modeling process, a prediction strategy of gradually sliding backwards is used, such as predicting the flow 1 month and 1 day in 2001, constructing a feature vector by using the flow from 29 days 12 months in 2000 to 31 days 12 months in 2000, and constructing the feature vector by using the data 12 months and 31 days in 2000 and before; predicting the flow rate at 1/2/2001 by constructing a feature vector by using the flow rate from 30/12/2000 to 1/2001, and predicting by constructing a feature vector by using data at 1/2001 and before; and so on.
The daily runoff prediction results of Model1-Model12 in 2001 are shown in FIG. 3;
and thirdly, reconstructing the prediction results of the models 1-Model12 and R by an ESMD algorithm to obtain a prediction sequence of the daily runoff in 2001 in Hua county station. The comparison result between the measured value and the predicted value of the daily runoff in 2001 in the Hua county station is shown in fig. 4.
The daily runoff prediction accuracy based on ESMD and NNBR is shown in Table 1, and both meet the requirement of 20% of the design error of the specification.
TABLE 1
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, are merely for convenience of description of the present invention, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.
Claims (4)
1. A daily runoff time series prediction method based on ESMD and NNBR is characterized by comprising the following steps:
s1, collecting historical actual measurement daily runoff time sequence data, decomposing the historical actual measurement daily runoff sequence by using an extreme point symmetric model decomposition (ESMD) to obtain a subsequence and a daily runoff sequence decomposition residual error;
s2, establishing a nearest neighbor sampling regression model NNBR for the subsequences obtained by decomposition in the step S1, and predicting each subsequence through the NNBR;
and S3, reconstructing the prediction result of each subsequence in the step S2 and the daily runoff sequence decomposition residual error obtained in the step S1 through an ESMD algorithm to obtain a prediction sequence of daily runoff.
2. The ESMD and NNBR based daily runoff time series predicting method according to claim 1, wherein said ESMD and NNBR based daily runoff time series predicting method further comprises an accuracy calculation of a daily runoff prediction result.
3. The ESMD and NNBR-based daily runoff time series prediction method according to claim 2, wherein the accuracy calculation indexes of the daily runoff prediction result comprise: relative error, average relative error level, deterministic coefficient, process yield.
4. The method for predicting the daily runoff time series based on the ESMD and the NNBR as claimed in claim 1, wherein the step S1 is a specific method for decomposing the historical measured daily runoff time series by using the ESMD, and comprises the following steps:
s1.1, calculating all extreme points in daily runoff time sequence data, wherein the extreme points comprise a maximum point and a minimum point;
s1.2, sequentially connecting all adjacent extreme points, and marking the middle point of a connecting line between the adjacent extreme points;
s1.3, respectively adding middle points of left and right boundaries of the extreme points by a linear difference method;
s1.4, constructing a plurality of interpolation curves by using the midpoints of connecting lines between adjacent extreme points and the midpoints of left and right boundaries;
s1.5, repeating the steps S1.1-S1.4 to carry out iterative computation on the average value of the interpolation curve to obtain a first subsequence of daily runoff time sequence data Y;
s1.6, repeating the steps S1.1-S1.5 to carry out iterative computation on the subsequence of the daily runoff time sequence data until the residual error does not exceed any extreme point in the daily runoff time sequence data, and obtaining the decomposition residual error of the daily runoff time sequence data;
s1.7, setting an integer interval, changing the iteration times on the integer interval, repeating the steps S1.1-S1.6, and calculating the variance sigma of the residual error2And making sigma/sigma0Graph against number of iterations, where σ0Is the standard deviation of daily runoff time series data;
s1.8, passage σ/σ0Obtaining a relation graph with the iteration times to obtain sigma/sigma0And (4) taking the value of the corresponding iteration times when the value is the minimum value, and repeating the steps from S1.1 to S1.6 to obtain the daily runoff sequence decomposition residual error.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010304163.4A CN111539564A (en) | 2020-04-17 | 2020-04-17 | Daily runoff time sequence prediction method based on ESMD and NNBR |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010304163.4A CN111539564A (en) | 2020-04-17 | 2020-04-17 | Daily runoff time sequence prediction method based on ESMD and NNBR |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111539564A true CN111539564A (en) | 2020-08-14 |
Family
ID=71978754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010304163.4A Pending CN111539564A (en) | 2020-04-17 | 2020-04-17 | Daily runoff time sequence prediction method based on ESMD and NNBR |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111539564A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112329339A (en) * | 2020-10-27 | 2021-02-05 | 河北工业大学 | Short-term wind speed prediction method for wind power plant |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102867106A (en) * | 2012-08-14 | 2013-01-09 | 贵州乌江水电开发有限责任公司 | Method and system for predicting short-term running water |
CN108876021A (en) * | 2018-05-31 | 2018-11-23 | 华中科技大学 | A kind of Medium-and Long-Term Runoff Forecasting method and system |
CN110490366A (en) * | 2019-07-15 | 2019-11-22 | 西安理工大学 | Runoff forestry method based on variation mode decomposition and iteration decision tree |
-
2020
- 2020-04-17 CN CN202010304163.4A patent/CN111539564A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102867106A (en) * | 2012-08-14 | 2013-01-09 | 贵州乌江水电开发有限责任公司 | Method and system for predicting short-term running water |
CN108876021A (en) * | 2018-05-31 | 2018-11-23 | 华中科技大学 | A kind of Medium-and Long-Term Runoff Forecasting method and system |
CN110490366A (en) * | 2019-07-15 | 2019-11-22 | 西安理工大学 | Runoff forestry method based on variation mode decomposition and iteration decision tree |
Non-Patent Citations (4)
Title |
---|
任逍迪,李继清,纪昌明: "三峡调蓄前后径流变化的多尺度分析" * |
段志鹏;李继清;: "基于极点对称模态分解的北京市降水特征分析" * |
王飞;王宗敏;杨海波;赵勇;: "基于SPEI的黄河流域干旱时空格局研究" * |
黄景光;吴巍;程璐瑶;于楠;陈波;: "基于小波支持向量机特征分类的日径流组合预测――以宜昌三峡水库为例" * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112329339A (en) * | 2020-10-27 | 2021-02-05 | 河北工业大学 | Short-term wind speed prediction method for wind power plant |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112508275B (en) | Power distribution network line load prediction method and equipment based on clustering and trend indexes | |
Stephenson et al. | Bayesian inference for extremes: accounting for the three extremal types | |
CN112116147A (en) | River water temperature prediction method based on LSTM deep learning | |
CN110942194A (en) | Wind power prediction error interval evaluation method based on TCN | |
Li et al. | An integrated missing-data tolerant model for probabilistic PV power generation forecasting | |
Jiang et al. | Day-ahead prediction of bihourly solar radiance with a Markov switch approach | |
CN110910004A (en) | Reservoir dispatching rule extraction method and system with multiple uncertainties | |
CN111695290A (en) | Short-term runoff intelligent forecasting hybrid model method suitable for variable environment | |
CN113256036B (en) | Power supply cost analysis and prediction method based on Prophet-LSTNet combined model | |
CN110490366A (en) | Runoff forestry method based on variation mode decomposition and iteration decision tree | |
CN103969412B (en) | A kind of dissolved oxygen concentration flexible measurement method based on group decision reasoning by cases | |
Zhang et al. | Transfer learning featured short-term combining forecasting model for residential loads with small sample sets | |
CN113780636A (en) | Solar radiation prediction method based on EMD-GRU-Attention | |
CN117543544A (en) | Load prediction method, device, equipment and storage medium | |
CN111539564A (en) | Daily runoff time sequence prediction method based on ESMD and NNBR | |
CN115659609A (en) | DTW-DCRNN-based chemical industry park noise prediction method | |
CN114091768A (en) | STL (Standard template library) and LSTM (local Scale TM) with attention mechanism based tourism demand prediction method | |
CN114266416A (en) | Photovoltaic power generation power short-term prediction method and device based on similar days and storage medium | |
CN117114190A (en) | River runoff prediction method and device based on mixed deep learning | |
CN116822742A (en) | Power load prediction method based on dynamic decomposition-reconstruction integrated processing | |
CN116865232A (en) | Wind speed error correction-based medium-and-long-term wind power prediction method and system | |
Xiao et al. | Crude oil price forecasting: a transfer learning based analog complexing model | |
Chhabra | Comparison of imputation methods for univariate time series | |
CN114925940A (en) | Holiday load prediction method and system based on load decomposition | |
Wang et al. | Short-term electricity sales forecasting model based on wavelet decomposition and LSTM |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200814 |
|
RJ01 | Rejection of invention patent application after publication |