CN110097205A - A kind of building load prediction weather forecast data preprocessing method - Google Patents
A kind of building load prediction weather forecast data preprocessing method Download PDFInfo
- Publication number
- CN110097205A CN110097205A CN201910199923.7A CN201910199923A CN110097205A CN 110097205 A CN110097205 A CN 110097205A CN 201910199923 A CN201910199923 A CN 201910199923A CN 110097205 A CN110097205 A CN 110097205A
- Authority
- CN
- China
- Prior art keywords
- data
- weather forecast
- building load
- prediction
- load prediction
- 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 24
- 238000007781 pre-processing Methods 0.000 title claims abstract description 7
- 238000005070 sampling Methods 0.000 claims abstract description 27
- 238000004088 simulation Methods 0.000 claims abstract description 9
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000010206 sensitivity analysis Methods 0.000 claims description 4
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims 1
- 240000002853 Nelumbo nucifera Species 0.000 claims 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000000342 Monte Carlo simulation Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 241000229175 Calotes Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000008570 general process Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009423 ventilation 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
- 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
- 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)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of building load prediction weather forecast data preprocessing methods, the first step, collect historical data, the input variable of load forecasting model is determined by analysis of history data, second step analyzes the back propagation net between the data of weather forecast of prediction time and the historical record of real time meteorological data there are error;Third step carries out error sampling simulation according to data of weather forecast of the back propagation net to prediction time, modified data of weather forecast is inputted in building load prediction model, amendment prediction time, relevant weather forecast inputted parameter;Realize the amendment of building load prediction model.The present invention can efficiently solve the uncertain problem of weather forecast data, correct weather forecast data by the back propagation net of analysis weather forecast data and practical weather data, for predicting building load.
Description
Technical field
The present invention relates to a kind of building load electric powder predictions more particularly to a kind of based on Monte Carlo random sampling
The building load prediction preprocess method of weather forecast data.
Background technique
Heating, ventilation and air-conditioning (HVAC) system account for 40% of building energy consumption or so, it means that it has very big section
It can potentiality.But the operation and management level of such system is usually lower, and the refrigerating capacity of equipment and actual demand mismatch, and leads to energy
Consumption is big.Exact load Predicting Technique is the basis of HVAC system running optimizatin, is conducive to formulate operation reserve according to load variations,
To improve the hot comfort of building, reducing energy consumption based theoretical.
With the fast development of the present computer technology, numerous load prediction technologies based on intelligent algorithm are answered
For in the operation control of HVAC system.Such as particle swarm algorithm, neural network algorithm and algorithm of support vector machine etc..These
Load prediction technology be based on data-driven, i.e., using a large amount of historical data sample being collected into, it is trained,
Test, establishes load forecasting model, for subsequent load prediction.In numerous input datas, meteorologic parameter is to dynamic
State load plays very important effect, has a significant impact to the actual consumption of building.And when using load prediction technology,
It is meteorological pre- in order to require when look-ahead, which goes out, builds the load at a certain moment within 24 hours futures using weather forecast data
Count off evidence and real-time meteorological data often have deviation, will cause in this way the load that is predicted using weather forecast data there is also
Certain error.
" the uncertain accuracy for influencing load prediction results of weather forecast " is that present invention technology urgently to be resolved is asked
Topic.
Summary of the invention
In order to overcome the shortcomings in the prior art, the present invention proposes that a kind of building load prediction weather forecast data are located in advance
Reason method is modified weather forecast data by Monte Carlo method of random sampling, makes for the uncertainty of weather forecast
It is closer with Practical Meteorological Requirements parameter, and revised data are used to predict load, to significantly improve the pre- of building load
Survey precision.
A kind of building load prediction weather forecast data preprocessing method of the invention, this method comprises the following steps:
The first step collects historical data, is analyzed the historical data and is determined including the use of Sensitivity Analysis
The meteorologic parameter type of prediction model input and the meteorologic parameter and history that the required moment is selected using correlation analysis
Load, the input parameter as building load prediction model;
Second step, analyzes between the data of weather forecast of prediction time and the historical record of real time meteorological data that there are errors
Back propagation net;
Third step carries out error random sampling to the data of weather forecast of prediction time according to the back propagation net
Simulation, the sampling results Δ x of each meteorologic factor back propagation neti, and this sampling results is used to correct former weather forecast number
According to Xi, correction formula is as follows:
Indicate revised weather report parameters, as the input parameter of building load prediction model, i indicate it is meteorological because
Plain serial number;It is used for correcting the data of weather forecast at moment to be predicted, be built finally, modified data of weather forecast is inputted
In load forecasting model, the amendment of building load prediction model input parameter is realized.
Compared with prior art, the good effect that the present invention can reach is as follows:
A kind of pretreatment of building load prediction weather forecast data based on Monte Carlo random sampling of the invention
Method can efficiently solve the uncertain problem of weather forecast data, pass through analysis weather forecast data and practical weather
The back propagation net of data corrects weather forecast data, for predicting building load.
Detailed description of the invention
Fig. 1 is a kind of building load prediction weather forecast data preprocessing method overall flow schematic diagram of the invention;
Fig. 2 is prediction time to shift to an earlier date 1 hour forecast temperature and the probability of error distribution map of actual temperature;
Fig. 3 is the probability of error scatter chart of revised data of weather forecast T (h-1) *.
Specific embodiment
Technical solution of the present invention is described in detail with reference to the accompanying drawings and examples.
As shown in Figure 1, for a kind of building load prediction weather forecast data preprocessing method overall flow of the invention
Schematic diagram, detailed process the following steps are included:
Step 1, the input variable for determining building load prediction model determine tool including the use of (1) Sensitivity Analysis
There is input of the sensibility meteorologic parameter as building load prediction model;And (2) correlation analysis is utilized, needed for selection
Input parameter of the meteorologic parameter and historical load at moment as building load prediction model;
There are errors between step 2, the data of weather forecast for carrying out prediction time and the historical record of real time meteorological data
Back propagation net analysis;
Step 3, in conjunction with back propagation net, first to the data of weather forecast of prediction time according to before back propagation net
Error sampling simulation is carried out, is used for correcting the data of weather forecast at moment to be predicted, it is finally that modified weather is pre-
Count off is according in input building load prediction model;
Step 4 establishes building load prediction model, obtains final building load prediction result.
Wherein, (1) Sensitivity Analysis, by the way that the size of relevant meteorologic parameter is taken turns doing same magnitude (usually
Take within ± 20%) change, to observe the affecting laws that load is changed by these factors, and with sensitivity coefficient SQFAs
Measure the index of sensibility size.These general processes are realized by simulation softward.By the meteorological file for modifying simulation softward
In corresponding meteorologic parameter, and simulated, and then calculate the size of sensitivity coefficient index.It is generally used for the gas of load prediction
As parameter include outdoor dry-bulb temperature, relative humidity, normal direction beam radia intensity, horizontal plane solar scattered radiation intensity,
Wind direction and wind speed.(2) correlation analysis is analyzed two or more variable elements for having correlation, to weigh
Measure the related intimate degree of two Variable Factors.Need there are certain connection or probability just can be between the element of correlation
Carry out correlation analysis.Its analysis method includes that Pearson correlation is related to Spearman;Before carrying out correlation analysis,
Want whether judgement sample is normal distribution, if so, with Pearson correlation, it is otherwise related with Spearman;And select phase relation
Number is greater than 0.3 meteorologic parameter and historical load.
Back propagation net analysis is needed by SPSS software realization, by each weather forecast factor and its actual weather because
In the error input SPSS software of element, error distribution estimation is carried out.Common data distribution type has normal distribution, uniformly divides
Cloth, Poisson distribution or exponential distribution etc..
In step 3, according to the back propagation net of each meteorologic factor, sampling simulation is carried out, and correct prediction time
Relevant weather forecast inputs parameter, and detailed process is as follows:
1) assume that the back propagation net of obtained each meteorologic factor is as shown in table 1:
Table 1
Serial number | Weather conditions | Back propagation net |
X1 | The forecast temperature of T (h)-prediction time | N(μ1, σ1 2) |
X2 | T (h-1)-prediction time shifts to an earlier date 1 hour forecast temperature | N(μ2, σ2 2) |
X3 | T (h-2)-prediction time shifts to an earlier date 2 hours forecast temperature | N(μ3, σ3 2) |
X4 | The forecast relative humidity of RH (h)-prediction time | N(μ4, σ4 2) |
X5 | RH (h-1)-prediction time shifts to an earlier date 1 hour forecast relative humidity | N(μ5, σ5 2) |
X6 | RH (h-2)-prediction time shifts to an earlier date 2 hours forecast relative humidity | N(μ6, σ6 2) |
… | … | … |
2) each meteorologic factor error random sampling procedure based on Monte Carlo method is write in MATLAB software, and is executed
The program can get the sampling results Δ x for each meteorologic factor back propagation net being based in 1)i(i indicates meteorologic factor sequence
Number), and this sampling results is used to correct former data of weather forecast Xi, formula is as follows:
Indicate revised weather report parameters, the input parameter as building load prediction model.
Method of random sampling principle in Monte Carlo therein is as follows:
Law of great number and central-limit theorem in probability theory are the theoretical basis of Monte Carlo method.Monte Carlo simulation side
The principle of method is that have probability characteristics when problem or object itself, can generate sampled result by computer simulation, can be with
According to the statistical value of sampling calculating parameter.Based on the two theorems, which can be expressed as follows.
Assuming that there is function:
Y=f (x1, X2..., Xn), (2)
Each variable X1,X2,…,XnProbability Characteristics it is known that these stochastic variables can be by directly or indirectly
Sampling obtain its value (x1,x2,…,xn), the then value y of function YiIt can be obtained by formula (2):
yi=f (xi1, xi2..., xin), (3)
Repeatedly (i=1,2 ..., m) by independent duplicate sampling, numerous sampling results y of function Y be can be obtained1,y2,…,
ym, such as formula (3), the characteristics of value Normal Distribution.
Finally, function Y and the probability distribution in relation to digital feature information can be close to reality when number realization is sufficiently large
Situation.Stable conclusion can be obtained by calculating its average value, such as formula (4):
The entity research object of the embodiment of the present invention is certain building of Tianjin, proposed vertical 24 hours in advance building loads
Prediction model, and using local meteorologic parameter as the key input parameter of building load prediction model.
It as shown in table 2, is training sample partial data example.It is general for the building load prediction model for shifting to an earlier date 24 hours
Be difficult obtain prediction time shift to an earlier date the information such as 1 hour to 3 hours historical load and solar radiation value, therefore the instruction of the present embodiment
Practicing sample portion to select June 16 to September temperature on the 15th, the real-time weather data of relative humidity and load data is training sample
This (totally 576 samples).
Table 2
Wherein, L (d-1, h) indicates mentioning the previous day and being the historical load of prediction time h for prediction time d;T(h),RH
(h) dry-bulb temperature, the relative humidity of prediction time are indicated;T (h-1), T (h-2), T (h-3) indicate the 1 small in advance of prediction time
When, 2 hours, 3 hours dry-bulb temperature;RH (h-1), RH (h-2) respectively indicate the phase of 1 hour in advance of prediction time, 2 hours
To humidity, d indicates the day where prediction time, and h indicates prediction time, and L () indicates historical load, and RH () indicates relative humidity.
Training sample may additionally include daily data of weather forecast in July (except weekend) totally 171 samples.
It is found by analysis, error Normal Distribution N [μ, σ between data of weather forecast and practical weather data2]。
In order to study the uncertain influence to load prediction precision of data of weather forecast, repaired using Monte Carlo method of random sampling
The input parameter (i.e. meteorological data) of positive SVM model.Then, pretreated data of weather forecast is input to building load prediction
In model.
It is distributed using the error that 19.0 software of IBM SPSS Statistics successively analyzes seven meteorological input parameters.
As shown in Fig. 2, being the probability of error between the dry-bulb temperature T (h-1) and actual temperature for prediction time shifting to an earlier date 1 hour
Scatter chart.Average error μ=0.588, standard deviation=1.799.Next, by Monte Carlo random sampling procedure
MATLAB is written, the stochastical sampling of the error delta x between data of weather forecast and practical weather data is realized, by number realization m
1000 are set as, and obtains one group of modified data of weather forecast T (h-1) * using corresponding calculation procedure.Formula is as follows:
T (h-1) *=T (h-1)+Δ x (6)
For example, the load in order to predict 9 points of July 3, it is known that prediction time shifts to an earlier date 1 hour weather forecast dry-bulb temperature T
It (h-1) is 27.2 DEG C.Using sampling simulation 1000 times based on Monte Carlo method, then sampling results such as Fig. 2 of T (h-1)
It is shown.The most common value of T (h-1) is close to 26.7C in sampling simulation result.In fact, statistics obtains after random sampling
Error delta x is -0.6 DEG C, and revised data of weather forecast T (h-1) * is 26.6 DEG C, it means that the desired value of T (h-1) is
It 26.6 DEG C, is compared with original 27.2 DEG C, closer true weather data, i.e., 26.0 DEG C.
Table 3 lists the data type comparison result of the input parameter of building load prediction model.The result is as use
Monte Carlo method corrects the example of weather forecast value and the actual value for predicting 9 cooling loads on the 3rd in July, it can be seen that covers
The special modified data of weather forecast of calot's method is closer to real data.Other samples have the same effect, as space is limited,
It is not repeated herein.
Table 3
Table 4 shows the probability of error distribution of each input parameter, is missed by the input parameter that SPSS statistical analysis obtains
The probability-distribution function that difference is followed.Process for correcting other parameters is similar to the process of parameter T (h-1).We are no longer
It is described herein more details.
Table 4
Claims (1)
1. a kind of building load prediction weather forecast data preprocessing method, which is characterized in that this method includes below scheme:
The first step collects historical data, is analyzed the historical data and determines prediction including the use of Sensitivity Analysis
The meteorologic parameter and history at moment needed for the meteorologic parameter type and utilization correlation analysis of mode input select are negative
Lotus, the input parameter as building load prediction model;
Second step analyzes the mistake between the data of weather forecast of prediction time and the historical record of real time meteorological data there are error
The poor regularity of distribution;
Third step carries out error sampling simulation to the data of weather forecast of prediction time according to the back propagation net,
The sampling results Δ x of each meteorologic factor back propagation neti, and this sampling results is used to correct former data of weather forecast Xi, repair
Positive formula is as follows:
Indicate revised weather report parameters, as the input parameter of building load prediction model, i indicates meteorologic factor sequence
Number;It is used for correcting the data of weather forecast at moment to be predicted, finally, modified data of weather forecast is inputted building load
In prediction model, the amendment of building load prediction model input parameter is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910199923.7A CN110097205A (en) | 2019-03-15 | 2019-03-15 | A kind of building load prediction weather forecast data preprocessing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910199923.7A CN110097205A (en) | 2019-03-15 | 2019-03-15 | A kind of building load prediction weather forecast data preprocessing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110097205A true CN110097205A (en) | 2019-08-06 |
Family
ID=67443185
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910199923.7A Pending CN110097205A (en) | 2019-03-15 | 2019-03-15 | A kind of building load prediction weather forecast data preprocessing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110097205A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111310126A (en) * | 2020-02-14 | 2020-06-19 | 天津大学 | Air conditioner load prediction method suitable for regional building in planning stage |
WO2021043180A1 (en) * | 2019-09-02 | 2021-03-11 | 山东大学 | Regional short-term energy power prediction method and system that take weather into consideration |
CN112633549A (en) * | 2020-11-19 | 2021-04-09 | 国网宁夏电力有限公司电力科学研究院 | Statistical rule-based load probability interval modeling method |
CN114881374A (en) * | 2022-07-11 | 2022-08-09 | 广东电网有限责任公司佛山供电局 | Multi-element heterogeneous energy consumption data fusion method and system for building energy consumption prediction |
CN115551317A (en) * | 2022-10-24 | 2022-12-30 | 南京群顶科技股份有限公司 | Load prediction method for data machine room operation control based on weather forecast |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930356A (en) * | 2012-11-16 | 2013-02-13 | 广东电网公司电力调度控制中心 | Short-term load forecast method based on meteorological factor sensitivity |
CN104573851A (en) * | 2014-12-19 | 2015-04-29 | 天津大学 | Meteorological temperature forecast-based building hourly load forecasting method |
CN106408223A (en) * | 2016-11-30 | 2017-02-15 | 华北电力大学(保定) | Short-term load prediction based on meteorological similar day and error correction |
CN107392368A (en) * | 2017-07-17 | 2017-11-24 | 天津大学 | Meteorological forecast-based office building dynamic heat load combined prediction method |
-
2019
- 2019-03-15 CN CN201910199923.7A patent/CN110097205A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930356A (en) * | 2012-11-16 | 2013-02-13 | 广东电网公司电力调度控制中心 | Short-term load forecast method based on meteorological factor sensitivity |
CN104573851A (en) * | 2014-12-19 | 2015-04-29 | 天津大学 | Meteorological temperature forecast-based building hourly load forecasting method |
CN106408223A (en) * | 2016-11-30 | 2017-02-15 | 华北电力大学(保定) | Short-term load prediction based on meteorological similar day and error correction |
CN107392368A (en) * | 2017-07-17 | 2017-11-24 | 天津大学 | Meteorological forecast-based office building dynamic heat load combined prediction method |
Non-Patent Citations (1)
Title |
---|
陈瑶琪: "基于典型天气类型计及随机预测误差的光伏发电短期预测研究", 《中国电力》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021043180A1 (en) * | 2019-09-02 | 2021-03-11 | 山东大学 | Regional short-term energy power prediction method and system that take weather into consideration |
CN111310126A (en) * | 2020-02-14 | 2020-06-19 | 天津大学 | Air conditioner load prediction method suitable for regional building in planning stage |
CN111310126B (en) * | 2020-02-14 | 2022-10-14 | 天津大学 | Air conditioner load prediction method suitable for regional building in planning stage |
CN112633549A (en) * | 2020-11-19 | 2021-04-09 | 国网宁夏电力有限公司电力科学研究院 | Statistical rule-based load probability interval modeling method |
CN114881374A (en) * | 2022-07-11 | 2022-08-09 | 广东电网有限责任公司佛山供电局 | Multi-element heterogeneous energy consumption data fusion method and system for building energy consumption prediction |
CN115551317A (en) * | 2022-10-24 | 2022-12-30 | 南京群顶科技股份有限公司 | Load prediction method for data machine room operation control based on weather forecast |
CN115551317B (en) * | 2022-10-24 | 2023-12-12 | 南京群顶科技股份有限公司 | Load prediction method for data machine room operation control based on weather forecast |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110097205A (en) | A kind of building load prediction weather forecast data preprocessing method | |
Chong et al. | Calibrating building energy simulation models: A review of the basics to guide future work | |
Coakley et al. | A review of methods to match building energy simulation models to measured data | |
Wu et al. | New insights into regional differences of the predictions of municipal solid waste generation rates using artificial neural networks | |
CN108428017B (en) | Wind power interval prediction method based on nuclear extreme learning machine quantile regression | |
CN109116444B (en) | PCA-kNN-based air quality model PM2.5Forecasting method | |
CN107730097B (en) | Bus load prediction method and device and computing equipment | |
CN114169254A (en) | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model | |
CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
CN114548509A (en) | Multi-type load joint prediction method and system for multi-energy system | |
CN106600029A (en) | Macro-economy predictive quantization correction method based on electric power data | |
CN113011455A (en) | Air quality prediction SVM model construction method | |
CN113779760A (en) | Power-statistics combined seasonal climate prediction method based on predictable climate modality | |
Dong et al. | Short-term building cooling load prediction model based on DwdAdam-ILSTM algorithm: A case study of a commercial building | |
Ghassemi et al. | Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings | |
CN117200223A (en) | Day-ahead power load prediction method and device | |
CN114428986A (en) | Design wind speed analysis method and device for area without actually measured wind speed data | |
CN112070307A (en) | Method and device for predicting energy source load in region | |
CN116960962A (en) | Mid-long term area load prediction method for cross-area data fusion | |
CN115577856A (en) | Method and system for predicting construction cost and controlling balance of power transformation project | |
CN115828441A (en) | Fan output scene generation and reduction method based on condition generation countermeasure network | |
Boxer et al. | A model-based decision support tool for building portfolios under uncertainty | |
CN109858699B (en) | Water quality quantitative simulation method and device, electronic equipment and storage medium | |
Wu et al. | On condition maintenance model for complex electromechanical equipments based on remaining useful life and wiener process | |
WO2020105151A1 (en) | Facility maintenance inspection assisting system and order of inspection determination method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190806 |
|
WD01 | Invention patent application deemed withdrawn after publication |