CN109636007A - A kind of water demands forecasting method and device based on big data - Google Patents
A kind of water demands forecasting method and device based on big data Download PDFInfo
- Publication number
- CN109636007A CN109636007A CN201811383557.2A CN201811383557A CN109636007A CN 109636007 A CN109636007 A CN 109636007A CN 201811383557 A CN201811383557 A CN 201811383557A CN 109636007 A CN109636007 A CN 109636007A
- Authority
- CN
- China
- Prior art keywords
- water
- principal component
- data
- model
- demands forecasting
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 89
- 238000013277 forecasting method Methods 0.000 title claims abstract description 20
- 238000000513 principal component analysis Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000002790 cross-validation Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000012628 principal component regression Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003287 bathing Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000008235 industrial water Substances 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009466 transformation 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention relates to water demands forecasting technical fields, and in particular to a kind of water demands forecasting method and device based on big data inputs the data of acquisition, and carries out data prediction using Principal Component Analysis and Lasso Feature Selection model;By establishing each department year water demands forecasting model, water demands forecasting result is obtained according to pretreated data, the disclosure uses principal component analysis model, three kinds of models of Lasso regression model and Support vector regression prediction model combine, lasso algorithm is applied again after having used principal component analysis further to screen principal component, it reduces to the requirement because of protonatomic mass, compared to existing technology, the present invention, which only needs to collect less influence factor data set, can find out the high water consumption of accuracy, water consumption is predicted within the shorter time while increasing substantially the precision of prediction of water consumption.
Description
Technical field
The present invention relates to water demands forecasting technical fields, and in particular to a kind of water demands forecasting method based on big data and
Device.
Background technique
Due to overpopulation, with the speed of water be significantly faster than environment from net velocity, lacked so as to cause freshwater resources are deficient, quilt
It is included in non-renewable resources.With the rapid development of economy, urban and rural residents industrial water and urbanite water consumption demand increasingly
Greatly, so that water prediction work becomes the key for grasping future developing trend in water resources management.And it reasonably predicts town and country and advises
Draw the water consumption in the time limit, make its with Urban-rural Development is practical is close, have to town and country construction from now on and development of crucial importance
Meaning.Pass through following water consumption of prediction, on the one hand, we can substantially estimate the water deficit in city and rural area, set about seeking
Solution is sought, realizes the rational management of water resource, reduces economic loss.On the other hand, water demands forecasting is water resources management
The important content of planning.If do not carried out water demands forecasting, China be just difficult to formulate in long-term water resources development and utilization overall rule
Draw and water supply planning, just will affect the realization of national economic plan.
Only solely feature is chosen using Principal Component Analysis in existing technology, chooses contribution margin and reaches certain
The influence factor of degree predicted, although such way compared with the original convenient and efficient many of way, when influencing
When the factor overwhelming majority and dependent variable Relationship Comparison are close, the feature screened by Principal Component Analysis is still very much, this
If sample, it cannot achieve the effect that want to make operand reduction by this method.
There is the influence factor of high contribution margin often to have much the prediction of an event result, if relying only on principal component point
Analysis method reduces influence factor selection range, this undoubtedly to reduce computation burden do not serve it is great.
Robert Tibshirani in 1996 is put forward for the first time LASSO algorithm, full name Least absolute shrinkage
And selection operator is translated into least absolute value convergence and selection operator, lasso trick algorithm, and this method is a kind of compression
Estimation, it obtains the model more refined by constructing a penalty, so that it compresses some coefficients, concurrently sets
Some coefficients are zero, therefore remain the advantages of subset is shunk, and are a kind of Biased estimator of the processing with multi-collinearity data.
On the basis of with Principal Component Analysis, then lasso algorithm is applied, precision of prediction can be significantly improved;It is main at
Point combined with lasso be substantially exactly the script factor linear combination, if script factor value amplitude is similar, generation
Principal component can also carry out certain compression, it is similar be allowed to amplitude, but direction is constant, so still hanging down even amplitude is different
Straight;Then it can be returned with these principal components, then apply lasso and delete coefficient value is small, such effect meeting
More preferably, because This further reduces to the requirement because of protonatomic mass.
And the more accurate efficiently prediction water consumption of the prior art how to be combined to become the problem of being worth further investigation.
Summary of the invention
The present invention provides a kind of water demands forecasting method and device based on big data, can increase substantially water consumption
Water consumption is predicted while precision of prediction within the shorter time.
A kind of water demands forecasting method based on big data provided by the invention, which is characterized in that the water demands forecasting
Method the following steps are included:
Step S1, the data of input acquisition;
Step S2, data prediction is carried out using Principal Component Analysis and Lasso Feature Selection model;
Step S3, each department year water demands forecasting model is established;
Step S4, water demands forecasting result is obtained.
Further, the factor x step S1 representative especially by selectionjAs the data of acquisition, j=is enabled
14, then include:
The family per capita disposable income x of annual each department1, water price x2, 1-14 years old population x3, 15-64 years old population
x4, 65 years old and the above population x5, do not went up learn number x6, primary school's degree culture number x7, the culture of middle school's degree number
x8, university degree culture number x9, use bathtub number x10, use shower number x11, faucet water saving device usage quantity x12、
Water-saving toilet bowl usage quantity x13, water-saving type laundry machine usage quantity x14, the water consumption of annual each department is denoted as y, acquisition is simultaneously
It inputs the water consumption y of annual each department, influence the factor x of water consumption1~x14。
Further, the treatment process of the step S2 is as follows:
Step S21, by the water consumption y of annual each department, the factor x of influence water consumption1~x14Standardization obtains y* i, xii *,
xi2 *,…,x* i14;
Step S22, the characteristic value and feature vector of correlation matrix R are asked;
Step S23, the number m of principal component is determined;
Step S24, Lasso Feature Selection model is applied again to the principal component of selection;
Step S25, the principal component that coefficient is 0 is rejected.
Further, the step S21 Plays mode is as follows:
Assuming that collecting data count is n item, n > 1, wherein the i-th data is xi, then formula is standardized are as follows:
Wherein,
Further, the step S22 specifically includes the following steps:
Step S221, correlation matrix is enabled
Wherein,
Step S222, by characteristic equation | λ Ι-R |=0, find out corresponding eigenvalue λi(i=1,2 ... ..., 14), wherein I is
Diagonal entry is 1, the matrix that other elements are 0;
Step S223, by eigenvalue λiIt sorts by descending sequence, i.e. λ1≥λ2≥…≥λ14≥0;
Step S224, it is found out respectively corresponding to eigenvalue λiFeature vector e, wherein e be to eigenvalue λjAsk homogeneous side
Journey group (R- λiE) the untrivialo solution of e=0.
Further, the step S23 specifically includes the following steps:
Take eigenvalue λ of the contribution rate of accumulative total up to 85% or more1,λ,2,…λmCorresponding preceding m principal component c1,c2,…,
cm, wherein m < p, p are the total quantity of principal component, principal component ciContribution rate are as follows:
Contribution rate of accumulative total are as follows:
Principal component regression (Principal-Components-Regression, PCR) is carried out on the basis of principal component
, make standardization dependent variable y*To m principal component c1,c2,…,cmMultiple linear regression;
If y*=i1c1+i2c2+…+imcm, due to c1,c2,…,cmIt is all standardized data x1 *,x2 *,…,x* 14It is linear
Combination, so also havingSo as to which standardized data is reduced into initial data;
Further, the step S24 is specifically included:
It is further sieved by factor of the Lasso method to the influence water consumption screened via Principal Component Analysis
Choosing is improved because of protonatomic mass, by Lasso parameter Estimation is defined as:
Wherein, β is regression coefficient vector, and λ is non-negative regular parameter, controls the complexity of model, λ is bigger, to spy
The punishment dynamics for levying more linear model are bigger, to finally obtain the less model of a feature;
Wherein,
Referred to as penalty term,
By determining parameter lambda, the smallest λ value of cross validation error is chosen, according to obtained λ value again model of fit.
Further, the step S3 specifically includes the following steps:
Step S31, by T={ (c1,y1),(c2,y2),...,(cn,yn) it is used as training set,
Wherein,
Step S32, prediction model is trained, and the real-time update training sample before carrying out subsequent time and predicting, i.e.,
Add the actual used water amount of last moment and the number of principal components evidence of selection and the data for removing most original;
Step S33, for sample (ci, yi), f (c is exported according to modeli) and true value yiBetween difference come calculate damage
It loses, and if only if f (ci)=yiWhen, loss is just zero;
Step S34, by f (xi) and yiBetween deviation be up to ε.Only as | f (xi)-yiLoss is just calculated when | > ε, when | f
(xi)-yiWhen |≤ε, then prediction is accurate.
Further, the step S4 is specifically included:
It will be input in water demands forecasting model, exported in each influence factor by the value of the finally obtained principal component of step S2
Under each year regional water consumption predicted value.
The present invention provides a kind of water demands forecasting device based on big data, and described device includes for storing computer journey
The memory that sequence instructs and the processor for executing program instructions, wherein when the computer program instructions are by the processing
When device executes, triggering described device executes method described in any of the above embodiments.
The beneficial effects of the present invention are: the present invention discloses a kind of water demands forecasting method and device based on big data, adopt
It is combined, is being used with three kinds of principal component analysis model, Lasso regression model and Support vector regression prediction model models
Lasso algorithm is applied again after principal component analysis further to screen principal component, is reduced to the requirement because of protonatomic mass, phase
Than in existing technology, the present invention only need to collect less influence factor data set can find out accuracy it is high use water
Amount, predicts water consumption while increasing substantially the precision of prediction of water consumption within the shorter time.
Detailed description of the invention
The invention will be further described with example with reference to the accompanying drawing.
Fig. 1 is a kind of flow chart of the water demands forecasting method based on big data of the embodiment of the present invention.
Specific embodiment
With reference to Fig. 1, a kind of water demands forecasting method based on big data provided in an embodiment of the present invention, including following step
It is rapid:
Step S1, the data of input acquisition;
There are many factors for influencing water consumption, such as income level, the population ages section of annual each department are distributed, receive an education
Degree, bathing mode, water price, water saving device service condition etc..
Wherein more representative factor is chosen in the present embodiment, comprising:
The family per capita disposable income x of annual each department1, water price x2, 1-14 years old population x3, 15-64 years old population
x4, 65 years old and the above population x5, do not went up learn number x6, primary school's degree culture number x7, the culture of middle school's degree number
x8, university degree culture number x9, use bathtub number x10, use shower number x11, faucet water saving device usage quantity x12、
Water-saving toilet bowl usage quantity x13, water-saving type laundry machine usage quantity x14, the water consumption of annual each department is denoted as y, acquisition is simultaneously
Input above data.
Step S2, data prediction is carried out using Principal Component Analysis and Lasso Feature Selection model;
Principal Component Analysis is that multiple variables are polynary to select one kind of less number significant variable by linear transformation
Statistical analysis technique, and comprehensive score can be calculated by this method, to filter out the relatively high factor of contribution margin
To carry out prediction work to reach the method for reducing calculation amount effect.
Wherein Principal Component Analysis and Lasso Feature Selection model are mainly used for Feature Selection, and treatment process is such as
Under:
Step S21, by the water consumption y of annual each department, the factor x of influence water consumption1~x14Standardization obtains y* i, xii *,
xi2 *,…,x* i14;
Standardized way is as follows:
Assuming that collecting data count is n item, n > 1, wherein the i-th data is xi, then formula is standardized are as follows:
Wherein,
Step S22, the characteristic value and feature vector of correlation matrix R are asked:
Solution mode is as follows:
Step S221, correlation matrix is enabled
Wherein,
Step S222, by characteristic equation | λ Ι-R |=0, find out corresponding eigenvalue λi(i=1,2 ... ..., 14), wherein I is
Diagonal entry is 1, the matrix that other elements are 0;
Step S223, by eigenvalue λiIt sorts by descending sequence, i.e. λ1≥λ2≥…≥λ14≥0;
Step S224, it is found out respectively corresponding to eigenvalue λiFeature vector e, wherein e be to eigenvalue λjAsk homogeneous side
Journey group (R- λiE) the untrivialo solution of e=0.
Step S23, it is determined as follows the number m of principal component;
Take eigenvalue λ of the contribution rate of accumulative total up to 85% or more1,λ,2,…λmCorresponding preceding m (m < p) a principal component c1,
c2,…,cm, wherein p is the total quantity of principal component, principal component ciContribution rate are as follows:
Contribution rate of accumulative total are as follows:
Principal component regression (Principal-Components-Regression, PCR) is carried out on the basis of principal component
, make standardization dependent variable y*To m principal component c1,c2,…,cmMultiple linear regression;
If y*=i1c1+i2c2+…+imcm, due to c1,c2,…,cmIt is all standardized data x1 *,x2 *,…,x* 14It is linear
Combination, so also havingSo as to which standardized data is reduced into initial data y=z0+
z1x1+z2x2+…+z14x14;
Step S24, Lasso Feature Selection model is applied again to the principal component of selection;
The coefficient of feature is compressed and certain regression coefficients is made to become 0 by Lasso method, and then reaches feature selecting
Purpose, model selection are substantially to seek the process of model sparse expression, and this process can be by being optimized to " a loss
And punishment " function problem complete.
Lasso method further screens the factor of the influence water consumption screened via Principal Component Analysis, mentions
Height is because of protonatomic mass.Lasso parameter Estimation is defined as:
Wherein, β is regression coefficient vector, and p is the total quantity of variable, and λ is non-negative regular parameter, controls the complexity of model
Degree, λ is bigger, and the punishment dynamics of the linear model more to feature are bigger, to finally obtain the less mould of a feature
Type;
Wherein,Referred to as penalty term determines parameter lambda by using cross-validation method, chooses cross validation error most
Small λ value, according to obtained λ value, with total data again model of fit, the value that λ is arranged in the present embodiment is 1000;
Step S25, the principal component that coefficient is 0 is rejected.
Step S3, using SVR (Support-Vector-Regression, support vector regression) model prediction each department
Annual water consumption;
Thought of the SVR when being fitted using support vector machines to carry out regression analysis to data, in the following manner
It is handled:
Step S31, by T={ (c1,y1),(c2,y2),...,(cn,yn) it is used as training set,
Wherein,
Step S32, prediction model is trained, and the real-time update training sample before carrying out subsequent time and predicting, i.e.,
Add the actual used water amount of last moment and the number of principal components evidence of selection and the data for removing most original;
Step S33, for sample (ci, yi), f (c is exported generally according to modeli) and true value yiBetween difference count
Loss is calculated, and if only if f (ci)=yiWhen, loss is just zero;
Step S34, by f (xi) and yiBetween deviation be up to ε, only as | f (xi)-yiLoss is just calculated when | > ε, when | f
(xi)-yiWhen |≤ε, it is believed that prediction is accurate.
Step S4: water demands forecasting result is obtained;
By step S3, an available water demands forecasting model, we only need will be by the finally obtained master of step S2
The value of ingredient is input in water demands forecasting model, more can accurately and quickly export each year ground under each influence factor
The predicted value of area's water consumption.
The present embodiment also provides a kind of water demands forecasting device based on big data, and described device includes calculating for storing
The memory of machine program instruction and processor for executing program instructions, wherein when the computer program instructions are described
When processor executes, triggering described device executes method described in any of the above embodiments.
The above, only presently preferred embodiments of the present invention, the invention is not limited to above embodiment, as long as
It reaches technical effect of the invention with identical means, all should belong to protection scope of the present invention.
Claims (10)
1. a kind of water demands forecasting method based on big data, which is characterized in that the water demands forecasting method includes following step
It is rapid:
Step S1, the data of input acquisition;
Step S2, data prediction is carried out using Principal Component Analysis and Lasso Feature Selection model;
Step S3, each department year water demands forecasting model is established;
Step S4, water demands forecasting result is obtained.
2. the water demands forecasting method according to claim 1 based on big data, which is characterized in that the step S1 is specific
By choosing representative factor xjAs the data of acquisition, j=14 is enabled, comprising:
The family per capita disposable income x of annual each department1, water price x2, 1-14 years old population x3, 15-64 years old population x4, 65 years old
And the above population x5, do not went up learn number x6, primary school's degree culture number x7, the culture of middle school's degree number x8, university
The number x of degree culture9, use bathtub number x10, use shower number x11, faucet water saving device usage quantity x12, it is water-saving
Closet usage quantity x13, water-saving type laundry machine usage quantity x14, the water consumption of annual each department is denoted as y, acquires and inputs every
The water consumption y of year each department, the factor x for influencing water consumption1~x14。
3. the water demands forecasting method according to claim 2 based on big data, which is characterized in that the place of the step S2
Reason process is as follows:
Step S21, by the water consumption y of annual each department, the factor x of influence water consumption1~x14Standardization obtains y* i, xii *,
xi2 *,…,x* i14;
Step S22, the characteristic value and feature vector of correlation matrix R are asked;
Step S23, the number m of principal component is determined;
Step S24, Lasso Feature Selection model is applied again to the principal component of selection;
Step S25, the principal component that coefficient is 0 is rejected.
4. the water demands forecasting method according to claim 3 based on big data, which is characterized in that in the step S21
Standardized way is as follows:
Assuming that collecting data count is n item, n > 1, the i-th data therein is xi, then formula is standardized are as follows:
Wherein,
5. the water demands forecasting method according to claim 4 based on big data, which is characterized in that the step S22 tool
Body the following steps are included:
Step S221, correlation matrix is enabled
Wherein,
Step S222, by characteristic equation | λ Ι-R |=0, find out corresponding eigenvalue λi(i=1,2 ... ..., 14), wherein I is diagonal
Line element is 1, the matrix that other elements are 0;
Step S223, by eigenvalue λiIt sorts by descending sequence, i.e. λ1≥λ2≥…≥λ14≥0;
Step S224, it is found out respectively corresponding to eigenvalue λiFeature vector e, wherein e be to eigenvalue λiSeek homogeneous equation group
(R-λiE) the untrivialo solution of e=0.
6. the water demands forecasting method according to claim 5 based on big data, which is characterized in that the step S23 tool
Body the following steps are included:
Take eigenvalue λ of the contribution rate of accumulative total up to 85% or more1,λ,2,…λmCorresponding preceding m principal component c1,c2,…,cm,
In, m < p, p are the total quantity of principal component, principal component ciContribution rate are as follows:
Contribution rate of accumulative total are as follows:
Make standardization dependent variable y*To m principal component c1,c2,…,cmMultiple linear regression:
If y*=i1c1+i2c2+…+imcm, thenIt is original to which standardized data to be reduced into
Data.
7. the water demands forecasting method according to claim 6 based on big data, which is characterized in that the step S24 tool
Body includes:
By Lasso parameter Estimation is defined as:
Wherein, β is regression coefficient vector, and λ is non-negative regular parameter, controls the complexity of model, and λ is bigger, to feature compared with
The punishment dynamics of more linear models are bigger, to finally obtain the less model of a feature;
Wherein,
Referred to as penalty term,
By determining parameter lambda, the smallest λ value of cross validation error is chosen, according to obtained λ value again model of fit.
8. the water demands forecasting method according to claim 7 based on big data, which is characterized in that the step S3 is specific
The following steps are included:
Step S31, by T={ (c1,y1),(c2,y2),...,(cn,yn) it is used as training set,
Wherein,
Step S32, prediction model is trained, and the real-time update training sample before carrying out subsequent time and predicting, that is, added
The actual used water amount of last moment and the number of principal components evidence of selection and the data for removing most original;
Step S33, for sample (ci,yi), f (c is exported according to modeli) and true value yiBetween difference come calculate loss, when
And if only if f (ci)=yiWhen, loss is just zero;
Step S34, by f (xi) and yiBetween deviation be up to ε, only as | f (xi)-yiLoss is just calculated when | > ε, when | f (xi)-
yiWhen |≤ε, then prediction is accurate.
9. any water demands forecasting method based on big data according to claim 1~8, which is characterized in that the step
Rapid S4 is specifically included:
It will be input in water demands forecasting model by the value of the finally obtained principal component of step S2, output is each under each influence factor
The predicted value of annual area water consumption.
10. a kind of water demands forecasting device based on big data, which is characterized in that described device includes for storing computer journey
The memory that sequence instructs and the processor for executing program instructions, wherein when the computer program instructions are by the processing
When device executes, triggering described device executes method as described in any one of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811383557.2A CN109636007A (en) | 2018-11-20 | 2018-11-20 | A kind of water demands forecasting method and device based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811383557.2A CN109636007A (en) | 2018-11-20 | 2018-11-20 | A kind of water demands forecasting method and device based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109636007A true CN109636007A (en) | 2019-04-16 |
Family
ID=66068386
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811383557.2A Pending CN109636007A (en) | 2018-11-20 | 2018-11-20 | A kind of water demands forecasting method and device based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109636007A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110674985A (en) * | 2019-09-20 | 2020-01-10 | 北京建筑大学 | Urban resident domestic water consumption prediction method and application thereof |
CN110956310A (en) * | 2019-11-14 | 2020-04-03 | 佛山科学技术学院 | Fish feed feeding amount prediction method and system based on feature selection and support vector |
CN111507507A (en) * | 2020-03-24 | 2020-08-07 | 重庆森鑫炬科技有限公司 | Big data-based monthly water consumption prediction method |
CN112561127A (en) * | 2020-11-27 | 2021-03-26 | 中国水利水电科学研究院 | Underground water pressure mining target-based alternative water source contribution rate balance analysis system |
CN113551296A (en) * | 2021-06-21 | 2021-10-26 | 顺德职业技术学院 | Daily water consumption adjusting method based on periodic variation |
CN116561393A (en) * | 2023-06-02 | 2023-08-08 | 黑龙江省水利科学研究院 | Ten thousand yuan GDP water consumption visualization system and method based on water consumption factors |
-
2018
- 2018-11-20 CN CN201811383557.2A patent/CN109636007A/en active Pending
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110674985A (en) * | 2019-09-20 | 2020-01-10 | 北京建筑大学 | Urban resident domestic water consumption prediction method and application thereof |
CN110956310A (en) * | 2019-11-14 | 2020-04-03 | 佛山科学技术学院 | Fish feed feeding amount prediction method and system based on feature selection and support vector |
CN110956310B (en) * | 2019-11-14 | 2023-04-28 | 佛山科学技术学院 | Fish feed dosage prediction method and system based on feature selection and support vector |
CN111507507A (en) * | 2020-03-24 | 2020-08-07 | 重庆森鑫炬科技有限公司 | Big data-based monthly water consumption prediction method |
CN111507507B (en) * | 2020-03-24 | 2023-04-18 | 重庆森鑫炬科技有限公司 | Big data-based monthly water consumption prediction method |
CN112561127A (en) * | 2020-11-27 | 2021-03-26 | 中国水利水电科学研究院 | Underground water pressure mining target-based alternative water source contribution rate balance analysis system |
CN112561127B (en) * | 2020-11-27 | 2022-10-25 | 中国水利水电科学研究院 | Underground water pressure mining target-based alternative water source contribution rate balance analysis system |
CN113551296A (en) * | 2021-06-21 | 2021-10-26 | 顺德职业技术学院 | Daily water consumption adjusting method based on periodic variation |
CN113551296B (en) * | 2021-06-21 | 2022-06-07 | 顺德职业技术学院 | Daily water consumption adjusting method based on periodic variation |
CN116561393A (en) * | 2023-06-02 | 2023-08-08 | 黑龙江省水利科学研究院 | Ten thousand yuan GDP water consumption visualization system and method based on water consumption factors |
CN116561393B (en) * | 2023-06-02 | 2024-01-30 | 黑龙江省水利科学研究院 | Ten thousand yuan GDP water consumption visualization system and method based on water consumption factors |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109636007A (en) | A kind of water demands forecasting method and device based on big data | |
CN105391083B (en) | Wind power interval short term prediction method based on variation mode decomposition and Method Using Relevance Vector Machine | |
Cai et al. | Regional sustainable development and spatial effects from the perspective of renewable energy | |
Xu et al. | Fuzzy best-worst method and its application in initial water rights allocation | |
CN108280552A (en) | Methods of electric load forecasting and system, storage medium based on deep learning | |
JP3637412B2 (en) | Time-series data learning / prediction device | |
CN106600037B (en) | Multi-parameter auxiliary load prediction method based on principal component analysis | |
CN112990500B (en) | Transformer area line loss analysis method and system based on improved weighted gray correlation analysis | |
CN103605878B (en) | A kind of general blood glucose prediction method based on data modeling and model transplantations | |
CN112733997A (en) | Hydrological time series prediction optimization method based on WOA-LSTM-MC | |
CN109411093A (en) | A kind of intelligent medical treatment big data analysis processing method based on cloud computing | |
CN112948123B (en) | Spark-based grid hydrological model distributed computing method | |
CN109816142A (en) | A kind of water resource precision dispensing system and distribution method | |
CN108960485A (en) | One provenance-lotus interacts the online dictionary learning probability optimal load flow method under electricity market | |
CN112132334A (en) | Method for predicting yield of urban domestic garbage | |
CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
CN109324953A (en) | A kind of energy consumption of virtual machine prediction technique | |
CN115422826A (en) | Intelligent energy-saving regulation and control method, device, equipment and storage medium for data center | |
CN110322063B (en) | Power consumption simulation prediction method and storage medium | |
CN109978172A (en) | A kind of resource pool usage forecast method and device based on extreme learning machine | |
CN108665090A (en) | Urban distribution network saturation load forecasting method based on principal component analysis Yu Verhulst models | |
CN106020982A (en) | Method for simulating resource consumption of software component | |
CN111160048B (en) | Translation engine optimization system and method based on cluster evolution | |
Chuang et al. | Note on the merge of two maximum models under same constraints | |
Sun et al. | Economic contribution and rebound effect of industrial water: The case of the Yangtze River Delta |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |