CN104268651A - Seasonal energy consumption data forecasting method based on wavelet multi-scale cubic exponential smoothing models - Google Patents
Seasonal energy consumption data forecasting method based on wavelet multi-scale cubic exponential smoothing models Download PDFInfo
- Publication number
- CN104268651A CN104268651A CN201410508162.6A CN201410508162A CN104268651A CN 104268651 A CN104268651 A CN 104268651A CN 201410508162 A CN201410508162 A CN 201410508162A CN 104268651 A CN104268651 A CN 104268651A
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- exponential smoothing
- seasonal
- item
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 52
- 238000009499 grossing Methods 0.000 title claims abstract description 36
- 230000001932 seasonal effect Effects 0.000 title claims abstract description 29
- 238000013277 forecasting method Methods 0.000 title abstract 3
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 238000012731 temporal analysis Methods 0.000 description 3
- 238000000700 time series analysis Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000714 time series forecasting Methods 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to a forecasting method for seasonal energy consumption data. According to the method, multi-scale resolving and reconstruction are carried out on the energy consumption data through wavelet analysis, and the energy consumption data are forecast in cooperation with cubic exponential smoothing models. The forecasting method includes the steps that three-layer multi-scale resolving is firstly carried out on the energy consumption data through wavelet analysis, then the cubic exponential smoothing models are respectively built for the data on the different scales, forecast values are calculated for the data on the different scales, and finally wavelet reconstruction is carried out on the forecast data on the different scales; that is, the wavelet reconstruction is carried out on the forecast values of detailed data and approximate data resolved on the third layer, and the forecast values of approximate data on the second layer are obtained; wavelet reconstruction is carried out in cooperation with the detailed portion of the second layer, and the approximate portion of the first layer is accordingly obtained; then wavelet reconstruction is carried out in cooperation with the first layer, and finally the forecast values of the energy consumption data are obtained. Multi-scale analysis is carried out on the energy consumption data, effective modeling is carried out carried out according to the features of the data on the different scales, and the forecasting accuracy can be improved.
Description
Technical field
The invention belongs to energy consumption data Forecasting Methodology.Wavelet analysis is utilized to carry out multi-resolution decomposition and reconstruct to energy consumption data, and the method that the Three-exponential Smoothing model taking seasonal factor into consideration is predicted energy consumption data.First utilize wavelet analysis to carry out multi-resolution decomposition to energy consumption data, then Three-exponential Smoothing model is set up respectively and computational prediction value to the data on different scale, finally the predicted data on each yardstick is carried out wavelet reconstruction, obtain the predicted value of energy consumption data.Multiscale analysis is carried out to energy consumption data, effective modeling can be carried out according to the data characteristics on different scale, improve the accuracy of prediction.
Background technology
In recent years, the economic development of China is swift and violent, and building energy consumption has occupied more than 30% of social total energy consumption, and has the trend risen year by year.Meanwhile, China is in the period of energy relative shortage, and building high energy consumption situation increases China's Pressure on Energy, and govern the sustainable development of national economy, building energy conservation has been very urgent.Therefore, monitoring and prediction Energy Consumption of Public Buildings becomes an important content of current Building Energy-saving Work.
At present, existing part building achieves energy consumption measure, have accumulated a large amount of energy consumption datas in operational process.How to utilize these a large amount of data fast and effectively prediction of energy consumption trend have directive significance to reality.Classical Time series analysis method prediction mainly contains determinacy time series analysis method and Random time sequence method two kinds.Determinacy Time series analysis method mainly comprises the method for moving average, exponential smoothing, the time Return Law and the season cycle foreast method etc.Determinacy time series forecasting features the main trend of sequence, simple, intuitive, is easy to calculate and use.But because Measures compare is rough, and supposition is strict, Shortcomings and limitation in prediction.Random sequence model is method the most frequently used now, classical model mainly contains autoregressive moving-average model, autoregressive conditional different Variance model etc., in the application of statistics field widely, but owing to being that these models have certain hypothesis usually, as normality, stationarity etc., energy consumption data can not meet these hypothesis usually completely.
Wavelet Analysis Theory as an emerging mathematical theory and method, among the research being applied to every field.On different scale the ability of Decomposition Sequence of wavelet theory by small echo uniqueness is introduced in data prediction, be the different different ingredients of characteristic by Time Series, carry out data modeling prediction respectively according to the characteristic of each several part again, thus effectively can improve the efficiency of data prediction.In view of the advantage of wavelet analysis, the present invention utilizes wavelet analysis to carry out multi-resolution decomposition and reconstruct to energy consumption data, and binding time series model carries out energy consumption data prediction.
Summary of the invention
The present invention proposes a kind of method predicted energy consumption data.The method, on the basis furtherd investigate building energy consumption data characteristics, utilizes wavelet analysis to carry out multi-resolution decomposition and reconstruct to time series data, thus obtains more information, lowers uncertainty and the complicacy of forecasting problem.Due to this kind of time series of energy consumption data, comprise a large amount of useless compositions, utilize wavelet analysis that signal is carried out multilayer decomposition, respectively detail data and approximate data Modling model are predicted, finally the data reconstruction after prediction can be improved the accuracy of prediction.
A seasonal effect in time series fluctuation is jointly changed by many factors and causes, and wherein seasonal move refers to the seasonal cyclical swing that sequence showed with change in season in a year.Seasonal move usually can the secular trend of obfuscated data.So in building energy consumption data prediction, the model that can process seasonal move must be selected.Three-exponential Smoothing model to predicting containing trend and seasonal time series simultaneously, thus can be predicted building energy consumption data comparatively accurately.Three-exponential Smoothing model comprises addition model, multiplied model and without seaconal model three kinds, and for this kind of changing factor of energy consumption data comparatively independently time series, addition model is more applicable.
Because Three-exponential Smoothing algorithm can process trend and the seasonality of data simultaneously, so this model comprises level item a
t, trend term b
twith item S in season
tthree parameters.These three parameters are determined by the recurrence relation between data, and recursion formula is defined as follows:
at＝α(X
t-S
t-s)+(1-α)(a
t-1+b
t-1) (1)
b
t＝β(a
t-a
t-1)+(1-β)b
t-1 (2)
S
t＝γ(X
t-a
t)+(1+γ)S
t-s (3)
Wherein X
tfor time series observed reading, the s in formula represents seasonal cycle length, and α, β and γ are smoothing parameter, and value is between interval [0,1].
Known or when estimating in level item, trend term and item in season three parameters, time series X
tk walk prediction can by following formulae discovery
Use Three-exponential Smoothing addition model predicted data, will calculated level item a
t, trend term b
twith item S in season
tthree parameter values, then predict according to predictor formula.Definition due to three parameters only gives the recurrence relation before and after parameter, so first will estimate the initial value of parameter.By setting up regression model to estimate initial parameter value, regression equation is
wherein,
for the p rank moving average of sequence, if data are predicted in units of month, then p gets 12; If predict in units of season, then p gets 4.Through regression estimates, level item a can be obtained
twith trend term b
tinitial value a
0and b
0.For item S in season
t, utilize raw data divided by the value after moving average, namely
can obtain the initial value of item in season, if sequence is monthly data, season, item initial value had 12, season data then have 4.
After the initial value obtaining three parameters, just can use recursion formula recursion go out the level item of energy consumption data Final Issue, trend term and season item.After obtaining the parameter of Final Issue, the predicted value of energy consumption data can by the predictor formula of Three-exponential Smoothing addition model
calculate, wherein, a
tfor the level item of sample Final Issue, b
tfor the trend term of sample Final Issue, S
t+k-sfor the item in season of sample Final Issue, s is seasonal cycle length, and k is prediction length.
Set up Three-exponential Smoothing model respectively in pairing approximation data and detail data and after predicting, wavelet reconstruction carried out to each layer predicted data obtained.The detail data of decompose third layer and the predicted value of approximate data carry out wavelet reconstruction, obtain the predicted value of the approximate data of the second layer; Carry out wavelet reconstruction in conjunction with second layer detail section, thus obtain the approximate part of ground floor; And then carry out wavelet reconstruction in conjunction with ground floor, finally obtain the predicted value of energy consumption data.
Accompanying drawing explanation
Fig. 1 sets up Three-exponential Smoothing model respectively in pairing approximation data and detail data and after predicting, carries out wavelet reconstruction to each layer predicted data obtained.The detail data of decompose third layer and the predicted value of approximate data carry out wavelet reconstruction, obtain the predicted value of the approximate data of the second layer; Carry out wavelet reconstruction in conjunction with second layer detail section, thus obtain the approximate part of ground floor; And then carry out wavelet reconstruction in conjunction with ground floor, finally obtain the predicted value of energy consumption data.
Embodiment
Step 1: collect data and to go forward side by side line number Data preprocess.
Collect the building to be predicted day power consumption data of nearest 2 years, and carry out the moon energy consumption data that pre-service obtains nearest 2 years.
Step 2: energy consumption data DB4 small echo is carried out three layers of decomposition.
By Wavelet Analysis Theory, can by signal wavelet decomposition on different frequency channels.Because the signal after decomposing is more single than original signal in frequency content, and wavelet decomposition has made smoothing processing to signal, and the time series after therefore decomposing is more much better than original time series.Energy consumption data DB4 small echo is carried out three layers of decomposition, obtain the approximate part V of third layer
3with the detail section W of first, second and third layer
1, W
2, W
3four groups of corresponding time series V
t, X
t, Y
tand Z
t.
Step 3: calculate the level item a of four groups of time serieses in Three-exponential Smoothing model respectively
t, trend term b
twith item S in season
tthe initial value value a of three parameters
0, b
0and S
t.
With the time series X that detail section W1 is corresponding
tfor example, by X
tsequence is obtained through 12 rank moving averages
namely
Set up regression model
Estimate initial parameter value and obtain level item a
twith trend term b
tinitial value a
0and b
0.For item S in season
t, utilize raw data X
tdivided by the value after moving average
namely
then can obtain the initial value S of item in season
t.
Step 4: use recursion formula recursion go out the level item of energy consumption data one's last year, trend term and season item.
Obtain level item, trend term and season item initial value value a
0, b
0and S
tafter, the recursion formula recursion of initial value being brought into parameter go out the level item of time series Final Issue, trend term and season item.
Step 5: utilize Three-exponential Smoothing predictor formula to carry out the prediction of six phases.
After calculating three parameters of time series Final Issue, by the predictor formula of Three-exponential Smoothing addition model
calculate seasonal effect in time series six phase predicted value, wherein, a
tfor the level item of sample sequence Final Issue, b
tfor the trend term of Final Issue, S
t+k-sfor the item in season of Final Issue, prediction length k=1,2 ..., 5,6.
Step 6: pairing approximation and details each several part seasonal effect in time series predicted value carry out wavelet reconstruction, obtain the predicted value of final energy consumption data.
The detail data of decompose small echo third layer and the predicted value of approximate data carry out wavelet reconstruction, obtain the predicted value of the approximate data of the second layer; Carry out wavelet reconstruction in conjunction with second layer detail section, obtain the approximate part of ground floor; Carry out wavelet reconstruction finally by ground floor detail data and approximate data, finally obtain six phase predicted values of energy consumption data.
Claims (6)
1. the seasonal energy consumption data predication method based on multi-scale wavelet Three-exponential Smoothing model, it is characterized in that utilizing wavelet analysis that signal is carried out multilayer decomposition, set up Three-exponential Smoothing model to detail data and approximate data respectively to predict, finally the data reconstruction after prediction is improved the accuracy of prediction.
2., as claimed in claim 1 based on the seasonal energy consumption data predication method of multi-scale wavelet Three-exponential Smoothing model, it is characterized in that the Three-exponential Smoothing model of seasonal move is considered in described employing.
A seasonal effect in time series fluctuation is jointly changed by many factors and causes, and wherein seasonal move refers to the seasonal cyclical swing that sequence showed with change in season in a year.Seasonal move usually can the secular trend of obfuscated data, so in building energy consumption data prediction, must select the model that can process seasonal move.Three-exponential Smoothing model to predicting containing trend and seasonal time series simultaneously, thus can be predicted building energy consumption data comparatively accurately.
3. as claimed in claim 1 based on the seasonal energy consumption data predication method of multi-scale wavelet Three-exponential Smoothing model, it is characterized in that level item in described Three-exponential Smoothing model, trend term and season item parameter method of estimation.
Level item a in Three-exponential Smoothing model
t, trend term b
twith item S in season
tthree parameters, determined by the recurrence relation between data, recursion formula is defined as follows:
a
t＝α(X
t-S
t-s)+(1-α)(a
t-1+b
t-1) (1)
b
t＝β(a
t-a
t-1)+(1-β)b
t-1 (2)
S
t＝γ(X
t-a
t)+(1+γ)S
t-s (3)
Wherein X
tfor time series observed reading, the s in formula represents seasonal cycle length, and α, β and γ are smoothing parameter, and value is between interval [0,1].
4., as claimed in claim 1 based on the seasonal energy consumption data predication method of multi-scale wavelet Three-exponential Smoothing model, it is characterized in that time series X in described Three-exponential Smoothing model
tk step prediction.
Known or when estimating in level item, trend term and item in season three parameters, time series X
tk walk prediction can by following formulae discovery
Use Three-exponential Smoothing addition model predicted data, will calculated level item a
t, trend term b
twith item S in season
tthree parameter values, then predict according to predictor formula.Definition due to three parameters only gives the recurrence relation before and after parameter, so first will estimate the initial value of parameter.By setting up regression model to estimate initial parameter value, regression equation is
wherein,
for the p rank moving average of sequence, if data are predicted in units of month, then p gets 12; If predict in units of season, then p gets 4.Through regression estimates, level item a can be obtained
twith trend term b
tinitial value a
0and b
0.For item S in season
t, utilize raw data divided by the value after moving average, namely
can obtain the initial value of item in season, if sequence is monthly data, season, item initial value had 12, season data then have 4.
5., as claimed in claim 1 based on the seasonal energy consumption data predication method of multi-scale wavelet Three-exponential Smoothing model, be use Three-exponential Smoothing addition model to carry out prediction of energy consumption data described in it is characterized in that.
After using recursion formula recursion to go out the level item of energy consumption data Final Issue, trend term and season item, can by the predictor formula of Three-exponential Smoothing addition model
calculate the predicted value of energy consumption data, wherein, a
tfor the level item of sample Final Issue, b
tfor the trend term of sample Final Issue, S
t+k-sfor the item in season of sample Final Issue, s is seasonal cycle length, and k is prediction length.
6. as claimed in claim 1 based on the seasonal energy consumption data predication method of multi-scale wavelet Three-exponential Smoothing model, it is characterized in that setting up Three-exponential Smoothing model respectively in pairing approximation data and detail data and after predicting, carrying out wavelet reconstruction to each layer predicted data obtained.Namely wavelet reconstruction is carried out to the detail data of third layer decomposition and the predicted value of approximate data, obtain the predicted value of the approximate data of the second layer; Carry out wavelet reconstruction in conjunction with second layer detail section, thus obtain the approximate part of ground floor; And then carry out wavelet reconstruction in conjunction with ground floor, finally obtain the predicted value of energy consumption data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410508162.6A CN104268651A (en) | 2014-09-28 | 2014-09-28 | Seasonal energy consumption data forecasting method based on wavelet multi-scale cubic exponential smoothing models |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410508162.6A CN104268651A (en) | 2014-09-28 | 2014-09-28 | Seasonal energy consumption data forecasting method based on wavelet multi-scale cubic exponential smoothing models |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104268651A true CN104268651A (en) | 2015-01-07 |
Family
ID=52160171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410508162.6A Pending CN104268651A (en) | 2014-09-28 | 2014-09-28 | Seasonal energy consumption data forecasting method based on wavelet multi-scale cubic exponential smoothing models |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268651A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105784479A (en) * | 2016-01-05 | 2016-07-20 | 山东科技大学 | Processing method for rubber particle concrete triaxial compression experimental data |
| CN107094093A (en) * | 2017-04-13 | 2017-08-25 | 北京网瑞达科技有限公司 | The periodic performance indications data predication method of the network equipment in network system |
| CN107783549A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | Single rotor plant protection unmanned plane obstacle avoidance system based on multi-sensor information fusion technology |
| CN107862476A (en) * | 2017-11-06 | 2018-03-30 | 国网山东省电力公司电力科学研究院 | A kind of metering table demand computational methods based on data analysis |
| CN110046744A (en) * | 2019-03-12 | 2019-07-23 | 平安科技（深圳）有限公司 | Energy consumption data method for early warning and relevant device based on trend prediction |
| CN111260147A (en) * | 2020-02-07 | 2020-06-09 | 河北工程大学 | Power generation capacity prediction method and device and terminal equipment |
| CN111898828A (en) * | 2020-03-09 | 2020-11-06 | 华能四川水电有限公司 | Hydroelectric power generation prediction method based on extreme learning machine |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930168A (en) * | 2012-11-06 | 2013-02-13 | 昆山北极光电子科技有限公司 | Analysis method of signal processing wavelets |
| CN103136598A (en) * | 2013-02-26 | 2013-06-05 | 福建省电力有限公司 | Monthly electrical load computer forecasting method based on wavelet analysis |
-
2014
- 2014-09-28 CN CN201410508162.6A patent/CN104268651A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930168A (en) * | 2012-11-06 | 2013-02-13 | 昆山北极光电子科技有限公司 | Analysis method of signal processing wavelets |
| CN103136598A (en) * | 2013-02-26 | 2013-06-05 | 福建省电力有限公司 | Monthly electrical load computer forecasting method based on wavelet analysis |
Non-Patent Citations (2)
| Title |
|---|
| 刘汉伟: "中央空调动态负荷预测及节能优化控制模式研究", 《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》 * |
| 朱韬析: "电力系统负荷预测", 《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105784479A (en) * | 2016-01-05 | 2016-07-20 | 山东科技大学 | Processing method for rubber particle concrete triaxial compression experimental data |
| CN105784479B (en) * | 2016-01-05 | 2018-05-18 | 山东科技大学 | A kind of processing method of rubber grain concrete triaxial compression test data |
| CN107783549A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | Single rotor plant protection unmanned plane obstacle avoidance system based on multi-sensor information fusion technology |
| CN107783549B (en) * | 2016-08-25 | 2020-12-08 | 大连楼兰科技股份有限公司 | Single-rotor-wing plant protection unmanned aerial vehicle obstacle avoidance system based on multi-sensor information fusion technology |
| CN107094093A (en) * | 2017-04-13 | 2017-08-25 | 北京网瑞达科技有限公司 | The periodic performance indications data predication method of the network equipment in network system |
| CN107862476A (en) * | 2017-11-06 | 2018-03-30 | 国网山东省电力公司电力科学研究院 | A kind of metering table demand computational methods based on data analysis |
| CN110046744A (en) * | 2019-03-12 | 2019-07-23 | 平安科技（深圳）有限公司 | Energy consumption data method for early warning and relevant device based on trend prediction |
| CN111260147A (en) * | 2020-02-07 | 2020-06-09 | 河北工程大学 | Power generation capacity prediction method and device and terminal equipment |
| CN111898828A (en) * | 2020-03-09 | 2020-11-06 | 华能四川水电有限公司 | Hydroelectric power generation prediction method based on extreme learning machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104268651A (en) | Seasonal energy consumption data forecasting method based on wavelet multi-scale cubic exponential smoothing models | |
| Bokde et al. | A novel imputation methodology for time series based on pattern sequence forecasting | |
| Hyndman et al. | Density forecasting for long-term peak electricity demand | |
| CN102346745B (en) | Method and device for predicting user behavior number for words | |
| CN105678403A (en) | Region saturation load prediction method based on model family decomposition and integration technology | |
| CN104751249A (en) | Space load prediction method | |
| CN102109619A (en) | System and method for predicting typhoon surge based on artificial intelligence | |
| CN103606013A (en) | User annual power consumption prediction method based on support vector machine | |
| Akpinar et al. | Estimating household natural gas consumption with multiple regression: Effect of cycle | |
| Salam et al. | Energy consumption prediction model with deep inception residual network inspiration and LSTM | |
| CN104217091A (en) | Website page view prediction method based on historical tendency weights | |
| CN103268525A (en) | WD-RBF (wavelet denoising-radial basis function)-based analogue prediction method of hydrological time sequence | |
| CN108205713A (en) | A kind of region wind power prediction error distribution determination method and device | |
| CN102184335A (en) | Fire disaster time sequence prediction method based on ensemble empirical mode decomposition and phase space reconstruction | |
| Yang et al. | Chaotic bayesian method based on multiple criteria decision making (MCDM) for forecasting nonlinear hydrological time series | |
| CN105260615A (en) | Grain consumption forecasting method | |
| CN105488595A (en) | Leading index construction method for monthly power consumption prediction model | |
| Öğünç et al. | Estimating the output gap for Turkey: an unobserved components approach | |
| Kosiorowski et al. | Forecasting of a hierarchical functional time series on example of macromodel for day and night air pollution in silesia region: a critical overview | |
| CN104573865A (en) | Method for predicting total energy consumption on the basis of fixed base energy consumption elasticity coefficient | |
| Jiang et al. | Fractal analysis of complex power load variations through adaptive multiscale filtering | |
| Mishra et al. | Sizing and quantity estimation for desilting tank of small hydropower projects—An analytical approach | |
| Davidsen et al. | The cost of ending groundwater overdraft on the North China Plain. | |
| Balashova et al. | The influence of energy production from renewable energy sources on energy efficiency and total factor productivity | |
| Lin et al. | Temporal scale features of medium and long-range hydrologic forecasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150107 |
|
| WD01 | Invention patent application deemed withdrawn after publication |