A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database
Traditional Heating, Ventilation and Air-conditioning systems operate on a fixed schedule, regardless of occupancy or external temperature. With the rise of smart buildings, building managers and owners are seeking ways to reduce energy consumption while maintaining occupant comfort. There are vario...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172529 |
| _version_ | 1826122097268621312 |
|---|---|
| author | Feng, Xue Eryan Bin Zainudin Wong, Hong Wen Tseng, King Jet |
| author2 | Energy Research Institute @ NTU (ERI@N) |
| author_facet | Energy Research Institute @ NTU (ERI@N) Feng, Xue Eryan Bin Zainudin Wong, Hong Wen Tseng, King Jet |
| author_sort | Feng, Xue |
| collection | NTU |
| description | Traditional Heating, Ventilation and Air-conditioning systems operate on a fixed schedule, regardless of occupancy or external temperature. With the rise of smart buildings, building managers and owners are seeking ways to reduce energy consumption while maintaining occupant comfort. There are various environmental and personal factors that impact thermal comfort levels. In this paper, we aim to develop a machine learning-based approach for precisely forecasting the thermal comfort levels of building occupants using the readily available ASHRAE RP-884 database. The dataset was first pre-processed using a k Nearest Neighbor (kNN)-based imputation method. Then, the RRelifF algorithm was used to select highly relevant and practically retrievable input features. Based on the selected features, four ensemble models were created to assess the relationship between input features and thermal comfort levels. A decision-making rule was employed to determine the credibility of each predictor, with only credible outputs selected. The credible outputs were aggregated to produce the final predicted mean vote (PMV) using Genetic Algorithm (GA) optimized coefficients. The testing results were promising, exhibiting high accuracy and a low Root Mean Squared Error (RMSE) value of 0.157 in the prediction of PMV. |
| first_indexed | 2024-10-01T05:42:56Z |
| format | Journal Article |
| id | ntu-10356/172529 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:42:56Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1725292023-12-12T15:37:40Z A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database Feng, Xue Eryan Bin Zainudin Wong, Hong Wen Tseng, King Jet Energy Research Institute @ NTU (ERI@N) Engineering::Civil engineering Thermal Comfort Machine Learning Traditional Heating, Ventilation and Air-conditioning systems operate on a fixed schedule, regardless of occupancy or external temperature. With the rise of smart buildings, building managers and owners are seeking ways to reduce energy consumption while maintaining occupant comfort. There are various environmental and personal factors that impact thermal comfort levels. In this paper, we aim to develop a machine learning-based approach for precisely forecasting the thermal comfort levels of building occupants using the readily available ASHRAE RP-884 database. The dataset was first pre-processed using a k Nearest Neighbor (kNN)-based imputation method. Then, the RRelifF algorithm was used to select highly relevant and practically retrievable input features. Based on the selected features, four ensemble models were created to assess the relationship between input features and thermal comfort levels. A decision-making rule was employed to determine the credibility of each predictor, with only credible outputs selected. The credible outputs were aggregated to produce the final predicted mean vote (PMV) using Genetic Algorithm (GA) optimized coefficients. The testing results were promising, exhibiting high accuracy and a low Root Mean Squared Error (RMSE) value of 0.157 in the prediction of PMV. Ministry of Education (MOE) Published version The paper was funded under the Singapore MOE Ignition Grant Energy Monitoring and Management Framework with Uncertainty Level Management. 2023-12-12T08:06:55Z 2023-12-12T08:06:55Z 2023 Journal Article Feng, X., Eryan Bin Zainudin, Wong, H. W. & Tseng, K. J. (2023). A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database. Energy and Buildings, 290, 113083-. https://dx.doi.org/10.1016/j.enbuild.2023.113083 0378-7788 https://hdl.handle.net/10356/172529 10.1016/j.enbuild.2023.113083 2-s2.0-85154552996 290 113083 en Energy and Buildings © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/bync-nd/4.0/). application/pdf |
| spellingShingle | Engineering::Civil engineering Thermal Comfort Machine Learning Feng, Xue Eryan Bin Zainudin Wong, Hong Wen Tseng, King Jet A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database |
| title | A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database |
| title_full | A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database |
| title_fullStr | A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database |
| title_full_unstemmed | A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database |
| title_short | A hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ASHRAE RP-884 database |
| title_sort | hybrid ensemble learning approach for indoor thermal comfort predictions utilizing the ashrae rp 884 database |
| topic | Engineering::Civil engineering Thermal Comfort Machine Learning |
| url | https://hdl.handle.net/10356/172529 |
| work_keys_str_mv | AT fengxue ahybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT eryanbinzainudin ahybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT wonghongwen ahybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT tsengkingjet ahybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT fengxue hybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT eryanbinzainudin hybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT wonghongwen hybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database AT tsengkingjet hybridensemblelearningapproachforindoorthermalcomfortpredictionsutilizingtheashraerp884database |