Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore
Commercial buildings in hot and humid tropical climates rely significantly on cooling systems to maintain optimal occupant comfort. A well-accurate day-ahead load profile prediction plays a pivotal role in planning the energy requirements of cooling systems. Despite the pressing need for effective d...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/14/2/397 |
| _version_ | 1797298718261641216 |
|---|---|
| author | Namitha Kondath Aung Myat Yong Loke Soh Whye Loon Tung Khoo Aik Min Eugene Hui An |
| author_facet | Namitha Kondath Aung Myat Yong Loke Soh Whye Loon Tung Khoo Aik Min Eugene Hui An |
| author_sort | Namitha Kondath |
| collection | DOAJ |
| description | Commercial buildings in hot and humid tropical climates rely significantly on cooling systems to maintain optimal occupant comfort. A well-accurate day-ahead load profile prediction plays a pivotal role in planning the energy requirements of cooling systems. Despite the pressing need for effective day-ahead cooling load predictions, current methodologies have not fully harnessed the potential of advanced deep-learning techniques. This paper aims to address this gap by investigating the application of innovative deep-learning models in day-ahead hourly cooling load prediction for commercial buildings in tropical climates. A range of multi-output deep learning techniques, including Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory networks (LSTMs), are employed to enhance prediction accuracy. Furthermore, these individual deep learning techniques are synergistically integrated to create hybrid models, such as CNN-LSTM and Sequence-to-Sequence models. Experiments are conducted to choose the time horizons from the past that can serve as input to the models. In addition, the influence of various categories of input parameters on prediction performance has been assessed. Historical cooling load, calendar features, and outdoor weather parameters are found in decreasing order of influence on prediction accuracy. This research focuses on buildings located in Singapore and presents a comprehensive case study to validate the proposed models and methodologies. The sequence-to-sequence model provided better performance than all the other models. It offered a CV-RMSE of 7.4%, 10%, and 6% for SIT@Dover, SIT@NYP, and the simulated datasets, which were 2.3%, 3%, and 1% less, respectively, than the base Deep Neural Network model. |
| first_indexed | 2024-03-07T22:40:03Z |
| format | Article |
| id | doaj.art-c95896c4837e4f269fc47f07af109016 |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-07T22:40:03Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-c95896c4837e4f269fc47f07af1090162024-02-23T15:10:07ZengMDPI AGBuildings2075-53092024-02-0114239710.3390/buildings14020397Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in SingaporeNamitha Kondath0Aung Myat1Yong Loke Soh2Whye Loon Tung3Khoo Aik Min Eugene4Hui An5Engineering Cluster, Singapore Institute of Technology, Singapore 138683, SingaporeDepartment of Engineering and Technology, Southeast Missouri State University, Cape Girardeau, MO 63701, USAEngineering Cluster, Singapore Institute of Technology, Singapore 138683, SingaporeSP Digital Pte. Co., Ltd., Singapore 349277, SingaporeSP Digital Pte. Co., Ltd., Singapore 349277, SingaporeEngineering Cluster, Singapore Institute of Technology, Singapore 138683, SingaporeCommercial buildings in hot and humid tropical climates rely significantly on cooling systems to maintain optimal occupant comfort. A well-accurate day-ahead load profile prediction plays a pivotal role in planning the energy requirements of cooling systems. Despite the pressing need for effective day-ahead cooling load predictions, current methodologies have not fully harnessed the potential of advanced deep-learning techniques. This paper aims to address this gap by investigating the application of innovative deep-learning models in day-ahead hourly cooling load prediction for commercial buildings in tropical climates. A range of multi-output deep learning techniques, including Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory networks (LSTMs), are employed to enhance prediction accuracy. Furthermore, these individual deep learning techniques are synergistically integrated to create hybrid models, such as CNN-LSTM and Sequence-to-Sequence models. Experiments are conducted to choose the time horizons from the past that can serve as input to the models. In addition, the influence of various categories of input parameters on prediction performance has been assessed. Historical cooling load, calendar features, and outdoor weather parameters are found in decreasing order of influence on prediction accuracy. This research focuses on buildings located in Singapore and presents a comprehensive case study to validate the proposed models and methodologies. The sequence-to-sequence model provided better performance than all the other models. It offered a CV-RMSE of 7.4%, 10%, and 6% for SIT@Dover, SIT@NYP, and the simulated datasets, which were 2.3%, 3%, and 1% less, respectively, than the base Deep Neural Network model.https://www.mdpi.com/2075-5309/14/2/397cooling load predictiondeep learningsequence-to-sequenceday-ahead predictions |
| spellingShingle | Namitha Kondath Aung Myat Yong Loke Soh Whye Loon Tung Khoo Aik Min Eugene Hui An Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore Buildings cooling load prediction deep learning sequence-to-sequence day-ahead predictions |
| title | Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore |
| title_full | Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore |
| title_fullStr | Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore |
| title_full_unstemmed | Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore |
| title_short | Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore |
| title_sort | enhancing day ahead cooling load prediction in tropical commercial buildings using advanced deep learning models a case study in singapore |
| topic | cooling load prediction deep learning sequence-to-sequence day-ahead predictions |
| url | https://www.mdpi.com/2075-5309/14/2/397 |
| work_keys_str_mv | AT namithakondath enhancingdayaheadcoolingloadpredictionintropicalcommercialbuildingsusingadvanceddeeplearningmodelsacasestudyinsingapore AT aungmyat enhancingdayaheadcoolingloadpredictionintropicalcommercialbuildingsusingadvanceddeeplearningmodelsacasestudyinsingapore AT yonglokesoh enhancingdayaheadcoolingloadpredictionintropicalcommercialbuildingsusingadvanceddeeplearningmodelsacasestudyinsingapore AT whyeloontung enhancingdayaheadcoolingloadpredictionintropicalcommercialbuildingsusingadvanceddeeplearningmodelsacasestudyinsingapore AT khooaikmineugene enhancingdayaheadcoolingloadpredictionintropicalcommercialbuildingsusingadvanceddeeplearningmodelsacasestudyinsingapore AT huian enhancingdayaheadcoolingloadpredictionintropicalcommercialbuildingsusingadvanceddeeplearningmodelsacasestudyinsingapore |