CN114118571A - Heating heat load prediction method based on LSTM deep learning - Google Patents
Heating heat load prediction method based on LSTM deep learning Download PDFInfo
- Publication number
- CN114118571A CN114118571A CN202111408084.9A CN202111408084A CN114118571A CN 114118571 A CN114118571 A CN 114118571A CN 202111408084 A CN202111408084 A CN 202111408084A CN 114118571 A CN114118571 A CN 114118571A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- lstm
- heating
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
A heating heat load prediction method based on LSTM deep learning comprises the steps of firstly, collecting heat load and weather historical data to obtain a sequence data set, and carrying out normalization processing; dividing the prepared data into a training set and a test set according to a proportion, establishing a heating load LSTM network model, adjusting internal parameters of the network, and finishing LSTM model fitting by using the training set data; combining the predictions with test data for overfitting evaluation of the model; after model evaluation and verification, inputting the online sampled data into a verified LSTM network to predict the heating load value at the future time. Finally, optimizing and upgrading the existing model, and circularly improving the prediction precision of the LSTM model; the LSTM can have better performance in a longer sequence, the heating heat load prediction method based on LSTM deep learning can record required data for a long time and predict on line, the prediction period is long, the heat load prediction precision is high, and the heat load prediction requirement of a heating season of a heating enterprise is met.
Description
Technical Field
The invention relates to the technical field of heating, in particular to a heating heat load prediction method based on LSTM deep learning.
Technical Field
The heating is a civil engineering, the cold and warm are not trivial, the winter heating relates to thousands of households, and the heating is an important heating project, and is the largest civil engineering at present. The heating system is composed of a heat source (supply side), a heat supply network, and a heat consumer (demand side). The heating is generally realized by adopting a central heating mode, and heat is supplied by a thermal power plant or a regional boiler. At present, the problems of rough adjustment, heat energy waste, unbalanced heating power and the like generally exist in a heating system, and a great improvement space is provided in the field of heating energy conservation.
Because the heating system is relatively complicated, the central heating load is influenced by main factors such as weather and the like in the operation process, and the heat load demand is constantly changed. The amount, characteristics and change rule of heating load are very important for the operation management, energy-saving optimization and atmospheric environment protection of a heating system.
The heating load prediction is to predict the magnitude of the heat load in a certain time period or moment in the future by comprehensively considering various relevant factors on the basis of mastering the change rule of the heat load, so that the heat source supply is matched with the requirements of a user side, and the efficient and energy-saving operation of a heating system is realized. If the supplied heat is not consistent with the required heat, excessive heating or insufficient heating can be caused, the requirements of people on production and life are influenced, energy waste and environmental pollution are caused, especially under the situation that the current coal supply and demand are short, a heating enterprise makes a heating load prediction in advance, and a coal-fired winter storage plan is made, so that the important effect is achieved on guaranteeing the heating of the livelihood. The existing heating load forecasting method is mainly used for singly and linearly forecasting according to weather and temperature or simply modeling according to time sequence of historical data, the forecasting time is short, the precision is low, and the medium-term and long-term heating production requirements of enterprises cannot be met.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a heating heat load prediction method based on LSTM deep learning, which predicts the heating load of the next heating season according to the heating load of the previous heating season and the multi-factor weather influence condition by introducing an LSTM model predicted by a multivariate time series; the long-term and short-term heating load prediction of a heat supply enterprise is met, the heat supply enterprise realizes stable production and supply of a ground heat source according to the demand of the heating load prediction, and the method has obvious economic and social benefits.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a heating heat load prediction method based on LSTM deep learning comprises the following steps:
step 1: collecting and preprocessing historical data; collecting data related to heat load production, including heat load data and weather data of heat supply production, arranging the data according to time to obtain a sequence sample data set, and carrying out normalization processing to enable the numerical value to be between [0 and 1] to obtain a data set as a sample for supervised learning;
step 2: dividing the data set into a training set and a testing set; the prepared sequence data are processed according to the following steps of 2: 1, dividing the data into a training set and a test set in proportion, and ensuring that each data set can represent a complete heating season sample;
and step 3: establishing a heating load prediction LSTM network model, and adjusting network internal parameters; predicting a load value as an output sequence future time by taking the load values of the current time and the past time in the sequence data set as an input sequence of an LSTM network prediction model, setting a prediction step length, and modeling an LSTM neural network, wherein the network internal parameter adjustment comprises the following steps: adjusting the learning rate and the iteration times according to a set value, acquiring an input weight, a cycle weight and a deviation, and adjusting parameters of a corresponding input gate, a corresponding forgetting gate, a corresponding selected gate and a corresponding output gate by using a gate activation function and a state activation function respectively;
and 4, step 4: fitting the model; training a heating load LSTM network model, inputting training set data subjected to normalization processing into the LSTM network model for training until the network converges;
and 5: overfitting evaluation of the model; after the model of step 4 is fitted, predicting the test data set obtained in step 2; displaying the model loss of the training set and the model loss of the testing set in a graph, and judging whether the model has an overfitting phenomenon;
step 6: model prediction; inputting the acquired online sampling data into the LSTM neural network evaluated and verified in the step 5 to predict the heating load value at the future time;
and 7: performing cyclic dynamic optimization on the model; and (3) setting accuracy, balance score and accuracy evaluation indexes to evaluate the prediction result, when the evaluation indexes exceed a set threshold, indicating that the deviation of the predicted value is large, executing the steps 1 to 5 every other period, optimizing and upgrading the model, and circularly improving the prediction precision of the LSTM model.
The invention has the beneficial effects that:
the invention relates to a heating heat load prediction method based on LSTM deep learning, wherein model supervision learning is set as follows: and predicting the heating load condition of the next heating season (time period) according to the heating load of the previous heating season (time period) and the weather influence condition. Firstly, collecting data related to heat load production from historical data of an enterprise production monitoring system, wherein the data comprises heat load data of heating production and weather data, arranging the data according to time to obtain a sequence sample data set, and performing normalization processing; dividing the prepared data into a training set and a test set according to a proportion; establishing a heating load prediction LSTM network model, and adjusting network internal parameters; inputting the normalized training set data into the heating load LSTM network model for model training, introducing a momentum method, dynamically modifying the learning rate of each parameter, and completing LSTM network model fitting; combining the prediction with the test data, adjusting the scale of the test data set by using the expected heating load, displaying the model training and test loss in a graph, and judging whether the model has an overfitting phenomenon; after model evaluation and verification, inputting online sampled data into a verified LSTM neural network to predict a heating load value at a future time; and finally, evaluating the result by setting accuracy, balance score and accuracy, and carrying out optimization upgrading on the existing model every other period for the condition that the difference of predicted values is large, thereby circularly improving the prediction precision of the LSTM model.
Drawings
FIG. 1 is a sample heating season heating load data used to establish a heating load prediction provided by the present invention.
FIG. 2 is a sample heating season weather data used to establish a heating load prediction as provided by the present invention.
Fig. 3 is a schematic diagram illustrating steps performed by the heating load prediction method according to the present invention.
Fig. 4 is a diagram of an LSTM network model for heating load prediction according to the present invention.
FIG. 5 is a graph of training, test loss assessment to determine overfitting of the LSTM model.
Detailed Description
The invention is further illustrated by the following detailed description in conjunction with the accompanying drawings.
Referring to fig. 3, a heating heat load prediction method based on LSTM deep learning includes the following steps:
step 1: collecting and preprocessing historical data; preparing an information data set for an LSTM model, collecting data related to heat load production from historical data of an enterprise production monitoring system, wherein the data comprises heat load data of heating production and weather data, arranging the data according to time to obtain a sequence sample data set, and carrying out normalization processing to enable the numerical value of the sequence sample data set to be between [0 and 1] to obtain the data set as a sample for supervised learning;
first, historical sample data is collected. These data are generally obtained from an enterprise production monitoring (SCADA/SIS/ERP) system through an API/SDK interface, and if the system cannot directly obtain heat load data, the data can be converted into heating heat load data on line from related index data (steam supply/water flow, steam supply/water temperature, return water temperature, steam supply/water pressure, and return water pressure), and the data are arranged according to time to obtain a sequence sample data set, and fig. 1 shows a heating load sequence sample set of a heating season (2018.11.10-2019.3.16) of a certain heating enterprise. The weather temperature mainly affected by the heating heat load is selected as the associated data, and the highest weather temperature and the lowest weather temperature of the same place in the same period and the heating load are collected to form an original data set, as shown in fig. 2. The original acquisition sequence is represented as: st＝{Xt(1),Xt(2),Xt(3),...Xt(u)},XtE to { U, I }, and carrying out normalized data preprocessing on the original collected data, wherein the calculation formula is as follows:
Xi＝(Xi-Xmin)/(Xmax-Xmin)
wherein: xi-a normalized value of the ith value in the collected sample;
Xi-the ith value in the collected sample;
Xmin-a minimum value in the collected sample;
Xmax-the maximum value in the collected sample.
Step 2: dividing the data set into a training set and a testing set; the prepared data are processed according to the following steps of 2: 1 ratio into a training set and a test set. To speed up model training, we fit the model using 2 years of data and then evaluate the remaining 1 year of data. Namely, the data scale of the training set and the test set is 2: 1, and each data set can represent a complete heating season sample.
And step 3: establishing a heating load prediction LSTM network model, and adjusting network internal parameters; predicting a load value as an output sequence future time by taking the load values of the current time and the past time in the sequence data set as an input sequence of an LSTM network prediction model, setting a prediction step length, and modeling an LSTM neural network, wherein the network internal parameter adjustment comprises the following steps: and adjusting the learning rate and the iteration times according to a set value, acquiring an input weight, a cycle weight and a deviation, and adjusting parameters of a corresponding input gate, a corresponding forgetting gate, a corresponding selected gate and a corresponding output gate by using a gate activation function and a state activation function respectively.
As shown in fig. 4. The LST model includes: the system comprises a data sampling layer a, a data preprocessing layer b, an input layer c, an LSTM layer d, a dropout layer e, a full connection layer f, a SoftMax layer g and a classification output layer h. Wherein: the layer a is used for collecting heating load and weather data of a heating season, the layer b is used for carrying out normalization preprocessing on the layer a data, the layer c is used for data diversity and format conversion, the layer d is used for LSTM network training, the layer e is used for monitoring network overfitting, and finally the layers f, g, h and i are used for outputting and optimizing results.
And 4, step 4: fitting the model; training a heating load LSTM network model, inputting training set data subjected to normalization processing into the LSTM network model for training until the network converges, and dynamically modifying the learning rate of each parameter by using an average absolute error (MAE) loss function and an Adam version with a random gradient descending, and introducing a momentum method to enable the parameter updating to have more chances to jump out of local optimum.
And 5: overfitting evaluation of the model; after fitting, we can predict the test data set obtained through step 2 and scale the test data set with the expected heating load. And displaying the model loss of the training set and the model loss of the test set in a graph, and judging whether the model has an overfitting phenomenon.
The error fraction of the model is calculated using the Root Mean Square Error (RMSE) of the unit errors that are the same as the variables from the initial predicted and actual values. The loss of training and testing is output at the end of each training epoch. Finally, the final RMSE of the model on the test data set is output, as shown in FIG. 5, and we can see that the model achieves good RMSE test results (3.836).
Step 6: and (5) model prediction. After model verification, inputting the acquired online sampling data into the LSTM neural network evaluated and verified in the step 5 to predict the heating load value at the future time.
And 7: performing cyclic dynamic optimization on the model; and (3) setting accuracy, balance score and accuracy evaluation indexes to evaluate the prediction result, indicating that the deviation of the predicted value is large when the evaluation indexes exceed a set threshold, executing the steps 1 to 5 every other period, optimizing and upgrading the model, and circularly improving the prediction precision of the LSTM model.
Claims (1)
1. A heating heat load prediction method based on LSTM deep learning is characterized by comprising the following steps:
step 1: collecting and preprocessing historical data; collecting data related to heat load production, including heat load data and weather data of heat supply production, arranging the data according to time to obtain a sequence sample data set, and carrying out normalization processing to enable the numerical value to be between [0 and 1] to obtain a data set as a sample for supervised learning;
step 2: dividing the data set into a training set and a testing set; the prepared sequence data are processed according to the following steps of 2: 1, dividing the data into a training set and a test set in proportion, and ensuring that each data set can represent a complete heating season sample;
and step 3: establishing a heating load prediction LSTM network model, and adjusting network internal parameters; predicting a load value as an output sequence future time by taking the load values of the current time and the past time in the sequence data set as an input sequence of an LSTM network prediction model, setting a prediction step length, and modeling an LSTM neural network, wherein the network internal parameter adjustment comprises the following steps: adjusting the learning rate and the iteration times according to a set value, acquiring an input weight, a cycle weight and a deviation, and adjusting parameters of a corresponding input gate, a corresponding forgetting gate, a corresponding selected gate and a corresponding output gate by using a gate activation function and a state activation function respectively;
and 4, step 4: fitting the model; training a heating load LSTM network model, inputting training set data subjected to normalization processing into the LSTM network model for training until the network converges;
and 5: overfitting evaluation of the model; after the model of step 4 is fitted, predicting the test data set obtained in step 2; displaying the model loss of the training set and the model loss of the testing set in a graph, and judging whether the model has an overfitting phenomenon;
step 6: model prediction; inputting the acquired online sampling data into the LSTM neural network evaluated and verified in the step 5 to predict the heating load value at the future time;
and 7: performing cyclic dynamic optimization on the model; and (3) setting accuracy, balance score and accuracy evaluation indexes to evaluate the prediction result, when the evaluation indexes exceed a set threshold, indicating that the deviation of the predicted value is large, executing the steps 1 to 5 every other period, optimizing and upgrading the model, and circularly improving the prediction precision of the LSTM model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111408084.9A CN114118571A (en) | 2021-11-24 | 2021-11-24 | Heating heat load prediction method based on LSTM deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111408084.9A CN114118571A (en) | 2021-11-24 | 2021-11-24 | Heating heat load prediction method based on LSTM deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114118571A true CN114118571A (en) | 2022-03-01 |
Family
ID=80372421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111408084.9A Pending CN114118571A (en) | 2021-11-24 | 2021-11-24 | Heating heat load prediction method based on LSTM deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114118571A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114777192A (en) * | 2022-04-22 | 2022-07-22 | 浙江英集动力科技有限公司 | Secondary network heat supply autonomous optimization regulation and control method based on data association and deep learning |
| CN115095907A (en) * | 2022-07-15 | 2022-09-23 | 唐山学院 | Intelligent heat supply energy-saving regulation and control method and system based on deep learning and storage medium |
| CN116293896A (en) * | 2023-01-30 | 2023-06-23 | 大唐保定热电厂 | Heating efficiency adjusting method and system for thermal power plant |
| CN116401935A (en) * | 2023-02-21 | 2023-07-07 | 哈尔滨工业大学 | Building dynamic thermal load neural network prediction method and system |
| CN117078047A (en) * | 2023-10-16 | 2023-11-17 | 华能济南黄台发电有限公司 | LSTM-based heat load prediction and distribution optimization method and system |
-
2021
- 2021-11-24 CN CN202111408084.9A patent/CN114118571A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114777192A (en) * | 2022-04-22 | 2022-07-22 | 浙江英集动力科技有限公司 | Secondary network heat supply autonomous optimization regulation and control method based on data association and deep learning |
| CN114777192B (en) * | 2022-04-22 | 2024-01-19 | 浙江英集动力科技有限公司 | Secondary network heat supply autonomous optimization regulation and control method based on data association and deep learning |
| CN115095907A (en) * | 2022-07-15 | 2022-09-23 | 唐山学院 | Intelligent heat supply energy-saving regulation and control method and system based on deep learning and storage medium |
| CN116293896A (en) * | 2023-01-30 | 2023-06-23 | 大唐保定热电厂 | Heating efficiency adjusting method and system for thermal power plant |
| CN116293896B (en) * | 2023-01-30 | 2023-09-01 | 大唐保定热电厂 | Heating efficiency adjusting method and system for thermal power plant |
| CN116401935A (en) * | 2023-02-21 | 2023-07-07 | 哈尔滨工业大学 | Building dynamic thermal load neural network prediction method and system |
| CN117078047A (en) * | 2023-10-16 | 2023-11-17 | 华能济南黄台发电有限公司 | LSTM-based heat load prediction and distribution optimization method and system |
| CN117078047B (en) * | 2023-10-16 | 2024-02-23 | 华能济南黄台发电有限公司 | LSTM-based heat load prediction and distribution optimization method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114118571A (en) | Heating heat load prediction method based on LSTM deep learning | |
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| CN104598985B (en) | Methods of electric load forecasting | |
| CN104484715A (en) | Neural network and particle swarm optimization algorithm-based building energy consumption predicting method | |
| CN108388962A (en) | A kind of wind power forecasting system and method | |
| CN103065202A (en) | Wind power plant ultrashort term wind speed prediction method based on combination kernel function | |
| CN114021848A (en) | Generating capacity demand prediction method based on LSTM deep learning | |
| CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
| CN115688993A (en) | Short-term power load prediction method suitable for power distribution station area | |
| CN115471014A (en) | Power grid enterprise electricity carbon consumption prediction method based on deep neural network | |
| Alanbar et al. | Energy Consumption Prediction Using Deep Learning Technique | |
| CN115409369A (en) | Comprehensive energy system reliability evaluation method based on mechanism and data hybrid driving | |
| CN110991747A (en) | Short-term load prediction method considering wind power plant power | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN116341705A (en) | Long-period memory network water quality parameter prediction method based on sparse label | |
| Ansari et al. | Wind power forecasting using artificial neural network | |
| Lv et al. | Research on short-term load forecasting approach for smart grid | |
| CN108345996A (en) | A kind of system and method reducing wind power checking energy | |
| CN113505909B (en) | Error compensation method for short-term wind power trend prediction | |
| Kowalski et al. | The comparison of linear models for PM10 and PM2. 5 forecasting | |
| CN114912716A (en) | Short-term power load prediction method and system based on bidirectional long-term and short-term memory network | |
| Tu et al. | Artificial neural networks in the estimation of monthly capacity factors of WECS in Taiwan | |
| Zhenhao et al. | Prediction of wind power ramp events based on deep neural network | |
| CN110070209B (en) | Short-term load prediction method of district heating system based on SD-DNNs | |
| Han et al. | Comparison of support vector machine, Gaussian process regression and decision tree models for energy consumption prediction of campus buildings |
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 |