Applicability of energy consumption prediction models in a department store: A case study
Obtaining an accurate picture of energy consumption in public spaces is a critical first step for predicting and enhancing energy efficiency. In practice, such calculations are often complicated, necessitating use of artificial intelligence models which can account for multiple factors. In this stud...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Case Studies in Thermal Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214157X2300686X |
| _version_ | 1827854821274681344 |
|---|---|
| author | Li-Yuan Chen Yen-Tang Chen Yu-Hsien Chen Da-Sheng Lee |
| author_facet | Li-Yuan Chen Yen-Tang Chen Yu-Hsien Chen Da-Sheng Lee |
| author_sort | Li-Yuan Chen |
| collection | DOAJ |
| description | Obtaining an accurate picture of energy consumption in public spaces is a critical first step for predicting and enhancing energy efficiency. In practice, such calculations are often complicated, necessitating use of artificial intelligence models which can account for multiple factors. In this study, we obtained four years of daily electricity usage, people flow, and ambient factor data from a department store in Taiwan to build an artificial intelligence model for predicting energy consumption. Previous literature on public spaces have mainly used Long Short-Term Memory (LSTM), gated recurrent unit (GRU), and other recurrent neural network (RNN) mechanisms. However, as our dataset spanned four years, we hypothesized that seasonal and trend decomposition using Loess (STL) was applicable as our data likely exhibited long cyclic patterns. We built and compared prediction results of three neural networks: LSTM-classic, STL, and GRU. As expected, the STL model provided better overall results (indicating a strong seasonality component in our data), as well as an optimal balance between accuracy and processing time. This case study provides a framework for others seeking to build neural networks for predicting and managing energy consumption in public spaces, and forms a theoretical basis for further discussion of energy efficiency topics. |
| first_indexed | 2024-03-12T11:36:34Z |
| format | Article |
| id | doaj.art-89c4bd4b1e924d61b3c2b7dbdd9dc355 |
| institution | Directory Open Access Journal |
| issn | 2214-157X |
| language | English |
| last_indexed | 2024-03-12T11:36:34Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Thermal Engineering |
| spelling | doaj.art-89c4bd4b1e924d61b3c2b7dbdd9dc3552023-09-01T05:02:05ZengElsevierCase Studies in Thermal Engineering2214-157X2023-09-0149103380Applicability of energy consumption prediction models in a department store: A case studyLi-Yuan Chen0Yen-Tang Chen1Yu-Hsien Chen2Da-Sheng Lee3Department of Energy and Refrigerating Air-Conditioning Engineering, National Taipei University of Technology, Taipei City, 10608, TaiwanDepartment of Energy and Refrigerating Air-Conditioning Engineering, National Taipei University of Technology, Taipei City, 10608, TaiwanDepartment of Energy and Refrigerating Air-Conditioning Engineering, National Taipei University of Technology, Taipei City, 10608, TaiwanCorresponding author.; Department of Energy and Refrigerating Air-Conditioning Engineering, National Taipei University of Technology, Taipei City, 10608, TaiwanObtaining an accurate picture of energy consumption in public spaces is a critical first step for predicting and enhancing energy efficiency. In practice, such calculations are often complicated, necessitating use of artificial intelligence models which can account for multiple factors. In this study, we obtained four years of daily electricity usage, people flow, and ambient factor data from a department store in Taiwan to build an artificial intelligence model for predicting energy consumption. Previous literature on public spaces have mainly used Long Short-Term Memory (LSTM), gated recurrent unit (GRU), and other recurrent neural network (RNN) mechanisms. However, as our dataset spanned four years, we hypothesized that seasonal and trend decomposition using Loess (STL) was applicable as our data likely exhibited long cyclic patterns. We built and compared prediction results of three neural networks: LSTM-classic, STL, and GRU. As expected, the STL model provided better overall results (indicating a strong seasonality component in our data), as well as an optimal balance between accuracy and processing time. This case study provides a framework for others seeking to build neural networks for predicting and managing energy consumption in public spaces, and forms a theoretical basis for further discussion of energy efficiency topics.http://www.sciencedirect.com/science/article/pii/S2214157X2300686XNeural networkEnergy efficiencyEnergy consumptionPublic spacesArtificial intelligence modeling |
| spellingShingle | Li-Yuan Chen Yen-Tang Chen Yu-Hsien Chen Da-Sheng Lee Applicability of energy consumption prediction models in a department store: A case study Case Studies in Thermal Engineering Neural network Energy efficiency Energy consumption Public spaces Artificial intelligence modeling |
| title | Applicability of energy consumption prediction models in a department store: A case study |
| title_full | Applicability of energy consumption prediction models in a department store: A case study |
| title_fullStr | Applicability of energy consumption prediction models in a department store: A case study |
| title_full_unstemmed | Applicability of energy consumption prediction models in a department store: A case study |
| title_short | Applicability of energy consumption prediction models in a department store: A case study |
| title_sort | applicability of energy consumption prediction models in a department store a case study |
| topic | Neural network Energy efficiency Energy consumption Public spaces Artificial intelligence modeling |
| url | http://www.sciencedirect.com/science/article/pii/S2214157X2300686X |
| work_keys_str_mv | AT liyuanchen applicabilityofenergyconsumptionpredictionmodelsinadepartmentstoreacasestudy AT yentangchen applicabilityofenergyconsumptionpredictionmodelsinadepartmentstoreacasestudy AT yuhsienchen applicabilityofenergyconsumptionpredictionmodelsinadepartmentstoreacasestudy AT dashenglee applicabilityofenergyconsumptionpredictionmodelsinadepartmentstoreacasestudy |