CN111476422A - L ightGBM building cold load prediction method based on machine learning framework - Google Patents
L ightGBM building cold load prediction method based on machine learning framework Download PDFInfo
- Publication number
- CN111476422A CN111476422A CN202010279924.5A CN202010279924A CN111476422A CN 111476422 A CN111476422 A CN 111476422A CN 202010279924 A CN202010279924 A CN 202010279924A CN 111476422 A CN111476422 A CN 111476422A
- Authority
- CN
- China
- Prior art keywords
- data
- ightgbm
- specifically
- training
- cold load
- 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 27
- 238000010801 machine learning Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000012795 verification Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 238000010219 correlation analysis Methods 0.000 claims abstract description 9
- 238000004140 cleaning Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000011985 exploratory data analysis Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 2
- 238000004378 air conditioning Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000012010 growth Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000002015 leaf growth Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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 building cold load prediction method based on L lightGBM under a machine learning framework, which comprises the steps of firstly selecting outdoor meteorological data and indoor environment data in a given time period to construct a data set, preprocessing the data of the data set, specifically comprising data cleaning, correlation analysis and standardization processing, dividing the preprocessed data set into a training set, a verification set and a test set, importing L lightGBM model and setting model parameters, loading the data set preprocessed in the step 2 into a Dataset object, training L lightGBM model and setting the training parameters, predicting cold load and outputting a predicted building cold load value.
Description
Technical Field
The invention relates to the technical field of building energy supply systems, in particular to a building cold load prediction method based on L ightGBM under a machine learning framework.
Background
The building energy consumption of China approximately accounts for 1/4 of the total social energy consumption, the air conditioning system is the most obvious factor influencing the building energy consumption, and in the actual operation of the building, the selection of the air conditioning system equipment is generally overlarge, which is bound to the low calculation accuracy of the design cold load. The number and size of air conditioning equipment, the division of the air conditioning system and the determination of an automatic control scheme are all determined by the building cold load, so that the realization of timely and accurate prediction of the building cold load is the basis for optimizing the design of the air conditioning system.
At present, three methods for predicting the cold load of a building are mainly used: firstly, use powerful load simulation software, simulate out building model in the computer, through setting up different parameters, can simulate the building cold load under the different conditions of calculating, however above-mentioned simulation process can be very consuming time, simulate personnel and also need possess abundant professional knowledge. In addition, the results of different simulation software calculations are also different; secondly, a unit area estimation algorithm is used, however, the method often causes a large cold load design value and low operation efficiency, and further causes unnecessary energy waste; thirdly, cold load prediction is carried out by utilizing statistics and machine learning methods, the method mainly comprises a BP neural network, a genetic algorithm, a support vector machine, wavelet analysis and the like, and although the models can predict the cold load of the building, the efficiency is low, the requirement on the performance of a computer is high, and the accuracy is insufficient.
Disclosure of Invention
The invention aims to provide a construction cold load prediction method based on L ightGBM under a machine learning framework, which is remarkably improved in the aspects of calculation efficiency and prediction accuracy compared with other prediction models, and improves the construction cold load prediction efficiency and accuracy.
The purpose of the invention is realized by the following technical scheme:
a building cold load prediction method based on L ightGBM under a machine learning framework, the method comprising:
and 6, inputting outdoor meteorological data and indoor environment data in specified time by using the trained model to obtain a building cold load predicted value in a corresponding time period.
According to the technical scheme provided by the invention, the method has the advantages that the calculation efficiency and the prediction accuracy are obviously improved compared with other prediction models, and the cold load prediction efficiency and accuracy of the building are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for predicting a building cold load based on L ightGBM under a machine learning framework according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a L eaf-wise leaf growth strategy in the L ightGBM model provided by an embodiment of the invention;
FIG. 3 is a data diagram of the first five elements of a processed data set according to an embodiment of the present invention;
fig. 4 is a diagram illustrating a relative error between a predicted value and a true value of a cooling load according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the present invention will be further described in detail with reference to the accompanying drawings, and as shown in fig. 1, a schematic flow chart of a method for predicting a building cold load based on L ightGBM under a machine learning framework provided by the embodiment of the present invention is shown, where the method includes:
in the step, the selected outdoor meteorological data comprise outdoor temperature and outdoor humidity; the indoor environment data includes indoor temperature, number of people in the room, and the like.
in this step, the process of preprocessing the data specifically includes:
1) firstly, cleaning data, wherein a data set is usually lacked due to various reasons, for example, some observed values are not recorded during investigation, and the example specifically identifies the lacked values through Exploratory Data Analysis (EDA), and then performs interpolation filling processing on the lacked values to realize data cleaning;
2) performing correlation analysis on data, considering that the correlation degree of partial input data and output data in the data is low, performing correlation analysis on the data, specifically performing correlation analysis by calculating a Pearson correlation coefficient and deleting the input data with the correlation coefficient | r | ≦ 0.1 of the output data so as to improve the prediction precision in order to accurately describe the linear correlation degree between the input data and the output data;
3) and then carrying out data standardization, specifically, carrying out min-max standardization on the data to enable the standardized data to be located between 0 and 1, further unifying the dimensions of the data, and eliminating the influence of dimension difference between the data on a prediction result, wherein a calculation formula of the min-max standardization is as follows:
wherein x represents input data; x is the number ofminRepresents the minimum value of the input data; x is the number ofmaxRepresents the maximum value of the input data; y represents normalized data.
in this step, in supervised machine learning, the preprocessed data set is often divided into 2-3 sets, i.e., training set (train set), verification set (validation set), and test set (test set).
In a specific implementation, the data of m months may be set as a training set and a verification set, and the division ratio train _ size is 0.9; and set the data for the first week of the m +1 month as the test set.
in this step, the imported L ightGBM module implements control and optimization of the algorithm by setting the following model parameters, and a dictionary is used to set the parameters, and the specific parameters and parameter settings are as follows:
(1) left _ rate: a learning rate, specifically set to 0.06;
(2) num _ leaves: the number of leaves of each tree is specifically set to be 32;
(3) max _ depth: the maximum learning depth is used for limiting the maximum depth of the tree model and controlling the overfitting phenomenon, and is specifically set to be 3;
(4) boosting _ type: a model lifting algorithm is specifically set as gbdt;
(5) min _ data: the minimum number of data in a leaf, used to control the overfitting phenomenon, was specifically set to 80;
(6) feature _ fraction, namely, selecting the proportion of the features to the total feature number, wherein the value is between 0 and 1, when the feature _ fraction is less than 0, L lightGBM randomly selects part of the features in each iteration, the feature _ fraction is used for controlling the proportion of the selected total feature number, the parameter can be used for accelerating the training speed and controlling the overfitting phenomenon, and the parameter is specifically set to be 0.95;
(7) bagging _ fraction: the proportion of the selected data to the total data volume is between 0 and 1, and is specifically set to 0.9, similar to feature _ fraction.
in this step, the Dataset is a local copy of the data source, and after the data is loaded from the data source, the connection with the data source is disconnected, so that the program performance can be improved.
L the ightGBM model is a gradient lifting frame, the training efficiency of the frame is faster, the used memory is lower, and the accuracy is higher, L the ightGBM model uses GOSS algorithm, EFB algorithm and Historgram algorithm, and has faster training speed and higher efficiency, the GOSS algorithm optimizes the sample sampling of the training set and keeps samples with larger gradient, the EFB algorithm binds mutually exclusive characteristics together so as to reduce characteristic dimension, and the Historgram algorithm disperses continuous characteristic values into K integers, so that when the splitting point of the characteristic is selected, only the discrete value of the sequencing Histogram needs to be traversed.
When the ightGBM model is trained L, a parameter list parameter (used for storing parameters required for training, including the parameters set in step 4 and required training parameters) and a data set (used for storing data for training) are required;
the set training parameters include: num _ boost _ round (iteration number of boosting algorithm) is 200, and early _ stopping _ rounds (early stopping is enabled to prevent overfitting, if the metric of one validation set is not raised in the early _ stopping _ rounds loop, the iteration is stopped) is 4000.
And 6, inputting outdoor meteorological data and indoor environment data in specified time by using the trained model to obtain a building cold load predicted value in a corresponding time period.
In the step, the trained model is used for predicting data needing prediction, specifically, outdoor meteorological data and indoor environment data of the first week of the m +1 month are input, and a building cold load prediction value of the first week of the m +1 month is output.
L the ightGBM model adopts a leaf-wise growing strategy, each time one leaf with the maximum splitting gain is found from all the current leaves, then the leaves are split, and the process is repeated, the leaf-wise growing strategy can reduce more errors and obtain better precision, the leaf-wise growing strategy L eaf-wise is shown in figure 2, the gray points represent the leaves with the maximum splitting gain, and the black points represent the leaves with the non-maximum splitting gain.
Furthermore, early stopping is started in the process of training the model, and a best _ iteration is used for obtaining a prediction result from the optimal iteration.
In addition, error analysis can be performed on the prediction result according to the test set divided in step 3, specifically, the following relative errors are adopted for analysis:
wherein e represents a relative error value, Y represents a test value,representing the predicted value.
It is noted that those skilled in the art will recognize that embodiments of the present invention are not described in detail herein.
The implementation process of the prediction method is illustrated by a specific example, and the example selects cold load data from 7/1/2019/8/30/8/morning to 20/afternoon of a certain office building to construct a data set, mainly aiming at a cold supply time period.
First, data preprocessing is performed on a data set, as shown in fig. 3, the data set is a first five-row data diagram of the processed data set provided by the embodiment of the present invention, the data set is divided, data of between 08:00 at 7/month 1 in 2019 and 31/month 20:00 in 2019 and 31/month in 2019 are divided into a training set and a verification set (a division ratio train _ size is 0.9), and data of between 08:00 at 8/month 1 in 2019 and 20:00 at 8/month 7 in 2019 are divided into a test set.
Then L lightGBM model is imported and model parameters are set, as shown in step 4, the processed data training set and verification set are loaded to a Dataset object, L lightGBM model is trained and the training parameters are set, as shown in step 5, finally, the trained model is used for predicting data needing prediction, specifically outdoor meteorological data and indoor environment data of the first week in 8 months are input, the model can output the predicted value of the building cold load of the first week in 8 months, and as shown in FIG. 4, the predicted value of the cold load and the relative error graph of the true value are provided by the embodiment of the invention.
In summary, the L ightGBM model introduced by the embodiment of the invention searches for the optimal segmentation point of the decision tree through a histogram decision tree algorithm, so that the purpose of reducing the memory can be achieved, the overfitting is limited by increasing the maximum depth of the decision tree, the prediction accuracy can be improved, the running speed can be improved through the histogram difference, better accuracy can be obtained through a leaf-by-leaf growth strategy (L eaf-wise) with depth limitation, and meanwhile, the maximum depth limitation for preventing overfitting is added in L eaf-wise, so that the calculation efficiency and the prediction accuracy are obviously improved compared with other prediction models.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A building cold load prediction method based on L ightGBM under a machine learning framework is characterized by comprising the following steps:
step 1, selecting outdoor meteorological data and indoor environment data in a given time period, and constructing a data set;
step 2, preprocessing the data of the data set, specifically comprising data cleaning, correlation analysis and standardization processing;
step 3, dividing the preprocessed data set into a training set, a verification set and a test set;
step 4, importing L an ightGBM model and setting model parameters;
step 5, loading the training set and the verification set preprocessed in the step 2 into a Dataset object, training L an ightGBM model and setting training parameters;
and 6, inputting outdoor meteorological data and indoor environment data in specified time by using the trained model to obtain a building cold load predicted value in a corresponding time period.
2. The method for predicting the cold load of the building based on L ightGBM under the machine learning framework as claimed in claim 1, wherein in the step 2, the pre-processing of the data is specifically as follows:
1) firstly, cleaning data, specifically identifying a missing value through Exploratory Data Analysis (EDA), and then performing interpolation filling processing on the missing value to realize data cleaning;
2) carrying out correlation analysis on the data, specifically carrying out correlation analysis by calculating a Pearson correlation coefficient, and deleting input data with the correlation coefficient | r | < 0.1 of output data so as to improve the prediction precision;
3) and then carrying out data standardization, specifically, carrying out min-max standardization on the data to enable the standardized data to be located between 0 and 1, further unifying the dimensions of the data, and eliminating the influence of dimension difference between the data on a prediction result, wherein a calculation formula of the min-max standardization is as follows:
wherein x represents input data; x is the number ofminRepresents the minimum value of the input data; x is the number ofmaxRepresents the maximum value of the input data; y represents normalized data.
3. The method for predicting the cold load of the building based on L ightGBM under the machine learning framework as claimed in claim 1, wherein the process of the step 3 is specifically as follows:
setting the data of m months as a training set and a verification set, and dividing the ratio train _ size to 0.9;
and set the data for the first week of the m +1 month as the test set.
4. The method for predicting cold load of L ightGBM building under machine learning frame as claimed in claim 1, wherein in step 4, the imported L ightGBM module implements algorithm control and optimization by setting the following model parameters:
(1) left _ rate: a learning rate, specifically set to 0.06;
(2) num _ leaves: the number of leaves of each tree is specifically set to be 32;
(3) max _ depth: the maximum learning depth is used for limiting the maximum depth of the tree model and controlling the overfitting phenomenon, and is specifically set to be 3;
(4) boosting _ type: a model lifting algorithm is specifically set as gbdt;
(5) min _ data: the minimum number of data in a leaf, used to control the overfitting phenomenon, was specifically set to 80;
(6) feature _ fraction: selecting the proportion of the features in the total number of the features, wherein the value is between 0 and 1; the parameter is used for accelerating the training speed and controlling the overfitting phenomenon, and is specifically set to be 0.95;
(7) bagging _ fraction: and selecting the proportion of the data in the total data quantity, wherein the value is between 0 and 1, and the value is specifically set to be 0.9.
5. The method for predicting the cold load of a building L ightGBM under the machine learning framework according to claim 1, wherein in step 5:
when the L ightGBM model is trained, a parameter list parameter for storing parameters required by training and a data set for storing training data are required;
the set training parameters include: the number of iterations num _ boost _ rounds of the boosting algorithm is 200, and early _ stopping _ rounds is 4000.
6. The method of predicting L ightGBM cold load under machine learning framework according to claim 1,
and further carrying out error analysis on the prediction result according to the verification set divided in the step 3, specifically adopting the following relative errors for analysis:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010279924.5A CN111476422A (en) | 2020-04-10 | 2020-04-10 | L ightGBM building cold load prediction method based on machine learning framework |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010279924.5A CN111476422A (en) | 2020-04-10 | 2020-04-10 | L ightGBM building cold load prediction method based on machine learning framework |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111476422A true CN111476422A (en) | 2020-07-31 |
Family
ID=71751543
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010279924.5A Pending CN111476422A (en) | 2020-04-10 | 2020-04-10 | L ightGBM building cold load prediction method based on machine learning framework |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111476422A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112488365A (en) * | 2020-11-17 | 2021-03-12 | 深圳供电局有限公司 | Load prediction system and method based on load prediction pipeline framework language |
CN112700167A (en) * | 2021-01-14 | 2021-04-23 | 华南理工大学 | Product quality index prediction method based on differential evolution |
CN113191418A (en) * | 2021-04-27 | 2021-07-30 | 华中科技大学 | Non-invasive building subentry cold load monitoring method based on outdoor meteorological parameters |
CN113378335A (en) * | 2021-05-07 | 2021-09-10 | 广州观必达数据技术有限责任公司 | Water supply network pressure prediction method and system based on machine learning |
CN113486433A (en) * | 2020-12-31 | 2021-10-08 | 上海东方低碳科技产业股份有限公司 | Method for calculating energy consumption shortage number of net zero energy consumption building and filling system |
CN113707228A (en) * | 2021-07-29 | 2021-11-26 | 北京工业大学 | LightGBM algorithm-based wet flue gas desulfurization optimization method |
CN114580758A (en) * | 2022-03-09 | 2022-06-03 | 苗韧 | Multi-city automatic energy load prediction method and system |
CN115015120A (en) * | 2022-06-20 | 2022-09-06 | 厦门宇昊软件有限公司 | Fourier infrared spectrometer and temperature drift online correction method thereof |
CN116227741A (en) * | 2023-05-05 | 2023-06-06 | 深圳市万物云科技有限公司 | Water chilling unit energy saving method and device based on self-adaptive algorithm and related medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779228A (en) * | 2012-06-07 | 2012-11-14 | 华南理工大学 | Method and system for online prediction on cooling load of central air conditioner in marketplace buildings |
WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
CN109409604A (en) * | 2018-10-30 | 2019-03-01 | 北京石油化工学院 | It is a kind of based on genetic algorithm-support vector machines cooling load prediction method |
US20190265768A1 (en) * | 2018-02-24 | 2019-08-29 | Hefei University Of Technology | Method, system and storage medium for predicting power load probability density based on deep learning |
CN110782658A (en) * | 2019-08-16 | 2020-02-11 | 华南理工大学 | Traffic prediction method based on LightGBM algorithm |
-
2020
- 2020-04-10 CN CN202010279924.5A patent/CN111476422A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779228A (en) * | 2012-06-07 | 2012-11-14 | 华南理工大学 | Method and system for online prediction on cooling load of central air conditioner in marketplace buildings |
WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
US20190265768A1 (en) * | 2018-02-24 | 2019-08-29 | Hefei University Of Technology | Method, system and storage medium for predicting power load probability density based on deep learning |
CN109409604A (en) * | 2018-10-30 | 2019-03-01 | 北京石油化工学院 | It is a kind of based on genetic algorithm-support vector machines cooling load prediction method |
CN110782658A (en) * | 2019-08-16 | 2020-02-11 | 华南理工大学 | Traffic prediction method based on LightGBM algorithm |
Non-Patent Citations (1)
Title |
---|
陈文凭 等: "基于人工神经网络的商场建筑冷负荷预测研究", 《湖南暖通空调》, 31 December 2007 (2007-12-31), pages 21 - 26 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112488365A (en) * | 2020-11-17 | 2021-03-12 | 深圳供电局有限公司 | Load prediction system and method based on load prediction pipeline framework language |
CN113486433A (en) * | 2020-12-31 | 2021-10-08 | 上海东方低碳科技产业股份有限公司 | Method for calculating energy consumption shortage number of net zero energy consumption building and filling system |
CN112700167A (en) * | 2021-01-14 | 2021-04-23 | 华南理工大学 | Product quality index prediction method based on differential evolution |
CN113191418A (en) * | 2021-04-27 | 2021-07-30 | 华中科技大学 | Non-invasive building subentry cold load monitoring method based on outdoor meteorological parameters |
CN113378335A (en) * | 2021-05-07 | 2021-09-10 | 广州观必达数据技术有限责任公司 | Water supply network pressure prediction method and system based on machine learning |
CN113707228A (en) * | 2021-07-29 | 2021-11-26 | 北京工业大学 | LightGBM algorithm-based wet flue gas desulfurization optimization method |
CN113707228B (en) * | 2021-07-29 | 2024-04-16 | 北京工业大学 | Wet flue gas desulfurization optimization method based on LightGBM algorithm |
CN114580758A (en) * | 2022-03-09 | 2022-06-03 | 苗韧 | Multi-city automatic energy load prediction method and system |
CN115015120A (en) * | 2022-06-20 | 2022-09-06 | 厦门宇昊软件有限公司 | Fourier infrared spectrometer and temperature drift online correction method thereof |
CN115015120B (en) * | 2022-06-20 | 2022-12-20 | 厦门宇昊软件有限公司 | Fourier infrared spectrometer and temperature drift online correction method thereof |
CN116227741A (en) * | 2023-05-05 | 2023-06-06 | 深圳市万物云科技有限公司 | Water chilling unit energy saving method and device based on self-adaptive algorithm and related medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111476422A (en) | L ightGBM building cold load prediction method based on machine learning framework | |
CN111695730B (en) | Vertical mill vibration prediction method and device based on ARIMA and RNN | |
CN112215442A (en) | Method, system, device and medium for predicting short-term load of power system | |
CN115097796B (en) | Quality control system and method for simulating big data and correcting AQL value | |
CN113449919A (en) | Power consumption prediction method and system based on feature and trend perception | |
CN112651543A (en) | Daily electric quantity prediction method based on VMD decomposition and LSTM network | |
CN112381673A (en) | Park electricity utilization information analysis method and device based on digital twin | |
CN113435595B (en) | Two-stage optimization method for network parameters of extreme learning machine based on natural evolution strategy | |
CN111505944B (en) | Energy-saving control strategy learning method, and method and device for realizing air conditioning energy control | |
CN109214610B (en) | Saturated power load prediction method based on long-term and short-term memory neural network | |
CN117450635B (en) | Fresh air system control method based on big data analysis | |
CN117072338B (en) | Self-adaptive oil injection control strategy system and optimization method for diesel engine | |
CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
CN111709585A (en) | Air conditioner load prediction method and device and storage medium | |
CN112443943A (en) | Model training method based on small amount of labeled data, control system and air conditioner | |
CN115829123A (en) | Natural gas demand prediction method and device based on grey model and neural network | |
CN113188243B (en) | Comprehensive prediction method and system for air conditioner energy consumption | |
CN116822672A (en) | Air conditioner cold load prediction optimization method and system | |
CN113705929A (en) | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion | |
CN114091723A (en) | Natural gas pipe network gas supply reliability detection method and device based on cross entropy theory | |
CN113570066B (en) | Data processing method, system, electronic device and storage medium | |
CN116235188A (en) | Method, apparatus and storage medium for generating predictive model of analysis object | |
CN111680720A (en) | Blast furnace molten iron silicon content prediction method based on improved CS-SVR model | |
CN117742683A (en) | Software development operating system | |
CN117574255B (en) | Slope safety coefficient prediction method based on pelican algorithm and support vector machine |
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: 20200731 |