Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks
Accurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neur...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/21/7439 |
| _version_ | 1797550032033939456 |
|---|---|
| author | Miguel Martínez Comesaña Lara Febrero-Garrido Francisco Troncoso-Pastoriza Javier Martínez-Torres |
| author_facet | Miguel Martínez Comesaña Lara Febrero-Garrido Francisco Troncoso-Pastoriza Javier Martínez-Torres |
| author_sort | Miguel Martínez Comesaña |
| collection | DOAJ |
| description | Accurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neural networks (ANNs) in buildings has grown considerably in recent years. The aim of this work is to study the thermal inertia of a building by developing an innovative methodology using multi-layered perceptron (MLP) and long short-term memory (LSTM) neural networks. This approach was applied to a public library building located in the north of Spain. A comparison between the prediction errors according to the number of time lags introduced in the models has been carried out. Moreover, the accuracy of the models was measured using the CV(RMSE) as advised by AHSRAE. The main novelty of this work lies in the analysis of the building inertia, through machine learning algorithms, observing the information provided by the input of time lags in the models. The results of the study prove that the best models are those that consider the thermal lag. Errors below 15% for thermal demand and below 2% for indoor temperatures were achieved with the proposed methodology. |
| first_indexed | 2024-03-10T15:22:42Z |
| format | Article |
| id | doaj.art-724e1b1a1f8c4575a9a3b0716bb63686 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:22:42Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-724e1b1a1f8c4575a9a3b0716bb636862023-11-20T18:18:32ZengMDPI AGApplied Sciences2076-34172020-10-011021743910.3390/app10217439Prediction of Building’s Thermal Performance Using LSTM and MLP Neural NetworksMiguel Martínez Comesaña0Lara Febrero-Garrido1Francisco Troncoso-Pastoriza2Javier Martínez-Torres3Department of Mechanical Engineering, Heat Engines and Fluids Mechanics, Industrial Engineering School, University of Vigo, Maxwell s/n, 36310 Vigo, SpainDefense University Center, Spanish Naval Academy, Plaza de España, s/n, 36920 Marín, SpainDepartment of Mechanical Engineering, Heat Engines and Fluids Mechanics, Industrial Engineering School, University of Vigo, Maxwell s/n, 36310 Vigo, SpainDepartment of Applied Mathematics I. Telecommunications Engineering School, University of Vigo, 36310 Vigo, SpainAccurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neural networks (ANNs) in buildings has grown considerably in recent years. The aim of this work is to study the thermal inertia of a building by developing an innovative methodology using multi-layered perceptron (MLP) and long short-term memory (LSTM) neural networks. This approach was applied to a public library building located in the north of Spain. A comparison between the prediction errors according to the number of time lags introduced in the models has been carried out. Moreover, the accuracy of the models was measured using the CV(RMSE) as advised by AHSRAE. The main novelty of this work lies in the analysis of the building inertia, through machine learning algorithms, observing the information provided by the input of time lags in the models. The results of the study prove that the best models are those that consider the thermal lag. Errors below 15% for thermal demand and below 2% for indoor temperatures were achieved with the proposed methodology.https://www.mdpi.com/2076-3417/10/21/7439neural networkLSTMMLPthermal inertiabuilding performance |
| spellingShingle | Miguel Martínez Comesaña Lara Febrero-Garrido Francisco Troncoso-Pastoriza Javier Martínez-Torres Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks Applied Sciences neural network LSTM MLP thermal inertia building performance |
| title | Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks |
| title_full | Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks |
| title_fullStr | Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks |
| title_full_unstemmed | Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks |
| title_short | Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks |
| title_sort | prediction of building s thermal performance using lstm and mlp neural networks |
| topic | neural network LSTM MLP thermal inertia building performance |
| url | https://www.mdpi.com/2076-3417/10/21/7439 |
| work_keys_str_mv | AT miguelmartinezcomesana predictionofbuildingsthermalperformanceusinglstmandmlpneuralnetworks AT larafebrerogarrido predictionofbuildingsthermalperformanceusinglstmandmlpneuralnetworks AT franciscotroncosopastoriza predictionofbuildingsthermalperformanceusinglstmandmlpneuralnetworks AT javiermartineztorres predictionofbuildingsthermalperformanceusinglstmandmlpneuralnetworks |