ABSTRACT
Thermal comfort, achieved by estimating the thermal sensation of occupants, has long been an important research topic. Numerous models and systems have been developed to improve the estimates of the accuracy of thermal comfort. Many either require extra devices to be installed; or require occupants to provide frequent feedback hindering the large scale deployability of the system. Data-driven models separate the process of collecting data used to establish the thermal comfort model from the process of deploying the model, making these models portable in deployment. Recent studies on data-driven thermal comfort models often make use of a single model. A single model can introduce large errors in practice, as thermal comfort is highly dependent on a variety of contextual factors, such as building type, location, and so on. In this paper, we for the first time study the contextual adaptation involved in predicting the thermal comfort of individuals by training multi-task models. We develop a Dynamic MUlti-task PrEdiction on Thermal Comfort (DUET) model. A key idea of our model is to use metadata to automatically define multi-task. Fortunately, there are ongoing efforts in metadata development in buildings, e.g., Brick. We extract metadata from Brick and evaluate our model using the public ASHRAE dataset. We demonstrate that in terms of error rate, DUET outperforms PMV model by 39% and STL by 31%.
- ASHRAE (Atlanta, Georgia). ANSI/ASHRAE Standard 55-2013: Thermal Environmental Conditions for Human Occupancy. 2013.Google Scholar
- Liang Yang, Zimu Zheng, et al. A domain-assisted data driven model for thermal comfort prediction in buildings. In ACM e-Energy, 2018.Google ScholarDigital Library
- Joyce Kim et al. Personal comfort models: predicting individuals' thermal preference using occupant heating and cooling behavior and machine learning. Building and Environment, 129:96--106, 2018.Google ScholarCross Ref
- Daniel de Roux et al. Tax fraud detection for under-reporting declarations using an unsupervised machine learning approach. In ACM SIGKDD, 2018.Google Scholar
- Richard de Dear, Gail Brager, and Donna Cooper. Developing an adaptive model of thermal comfort and preference. FINAL REPORT ASHRAE RP-884, 1997.Google Scholar
- Bharathan Balaji, Arka Bhattacharya, Gabriel Fierro, Jingkun Gao, et al. Brick: Towards a unified metadata schema for buildings. In ACM BuildSys'16.Google Scholar
- ISO 7730: 2005. Ergonomics of the thermal environment - Analytical determination and interpretation of thermal comfort using calculation of the pmv and ppd indices and local thermal comfort criteria.Google Scholar
- Peter Xiang Gao and Srinivasan Keshav. Spot: a smart personalized office thermal control system. In Proc. ACM e-Energy'13, pages 237--246.Google Scholar
- Peter Xiang Gao and Srinivasan Keshav. Optimal personal comfort management using spot+. In ACM BuildSys'13, pages 1--8.Google Scholar
- Alimohammad Rabbani and Srinivasan Keshav. The spot* personal thermal comfort system. In Proc. ACM BuildSys'16, pages 75--84.Google Scholar
- Varick L Erickson and Alberto E Cerpa. Thermovote: participatory sensing for efficient building hvac conditioning. In Proc. ACM BuildSys'12, pages 9--16.Google Scholar
- Abraham Hang-yat Lam et al. An occupant-participatory approach for thermal comfort enhancement and energy conservation in buildings. In ACM e-Energy'14.Google Scholar
- Shaozhi Ye and S Felix Wu. Estimating the size of online social networks. International Journal of Social Computing and Cyber-Physical Systems, 2011.Google ScholarCross Ref
- SenSys/BuildSys 2019. The data: Acquisition to analysis (data) workshop. https://workshopdata.github.io/DATA2019/, 2019.Google Scholar
- Zheng Yang and Burcin Becerik-Gerber. The coupled effects of personalized occupancy profile based hvac schedules and room reassignment on building energy use. Energy and Buildings, 78:113--122, 2014.Google ScholarCross Ref
- Wei Zhang et al. Thermal comfort modeling for smart buildings: A fine-grained deep learning approach. IEEE Internet of Things Journal, 2018.Google Scholar
- Juha Reunanen. Overfitting in making comparisons between variable selection methods. Journal of Machine Learning Research, 3(Mar):1371--1382, 2003.Google Scholar
- Jason Koh, Dezhi Hong, Rajesh Gupta, Kamin Whitehouse, Hongning Wang, and Yuvraj Agarwal. Plaster: An integration, benchmark, and development framework for metadata normalization methods. In ACM BuildSys'18.Google Scholar
- Gabe Fierro et al. Mortar: an open testbed for portable building analytics. In ACM BuildSys'18, pages 172--181.Google Scholar
- Rich Caruana. Multitask learning. Machine Learning, 28(1):41--75, 1997.Google ScholarDigital Library
- Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345--1359, 2010.Google ScholarDigital Library
- Yu Zhang and Qiang Yang. A survey on multi-task learning. arXiv preprint arXiv:1707.08114, 2017.Google Scholar
- Z. Wu et al. Deep neural networks employing multi-task learning and stacked bottleneck features for speech synthesis. In IEEE ICASSP, pages 4460--4464, 2015.Google Scholar
- C. Yuan et al. Multi-task sparse learning with beta process prior for action recognition. In Proceedings of IEEE CVPR, pages 423--429, 2013.Google Scholar
- X. Wang et al. Boosted multi-task learning for face verification with applications to web image and video search. In Proc. of IEEE CVPR, pages 142--149, 2009.Google Scholar
- Zimu Zheng, Yuqi Wang, Quanyu Dai, Huadi Zheng, and Dan Wang. Metadata-driven task relation discovery for multi-task learning. In IJCAI, 2019.Google ScholarCross Ref
- Jiayu Zhou et al. A multi-task learning formulation for predicting disease progression. In Proceedings of the 17th ACM SIGKDD, pages 814--822, 2011.Google Scholar
- Wikipedia. Metadata. https://en.wikipedia.org/wiki/Metadata, 2018.Google Scholar
- Xianchao Zhang, Xiaotong Zhang, and Han Liu. Self-adapted multi-task clustering. In IJCAI, pages 2357--2363, 2016.Google ScholarDigital Library
- Chen et al. XGBoost: A scalable tree boosting system. In Proc. ACM KDD'16.Google Scholar
- Zimu Zheng et al. Data driven chiller sequencing for reducing hvac electricity consumption in commercial buildings. In ACM e-Energy, 2018.Google ScholarDigital Library
- Qiong Chen et al. Data-driven task allocation for multi-task transfer learning on the edge. In IEEE ICDCS, pages 1620--1626, 2019.Google Scholar
- Zheng et al. An edge based data-driven chiller sequencing framework for hvac electricity consumption reduction in commercial buildings. In IEEE T-SUSC'19.Google Scholar
Index Terms
- DUET: Towards a Portable Thermal Comfort Model
Recommendations
Numerical Simulation and Experimental Research on Air Conditioning Terminal Combined by Capillary Ceiling and Displacement Ventilation
ICECE '10: Proceedings of the 2010 International Conference on Electrical and Control EngineeringIt introduces a new air conditioning terminal, combined by capillary ceiling and displacement ventilation, to keep indoor thermal comfort and air quality. Both ceiling radiation heating model and air conditioning terminal model combined by capillary ...
Flow analysis inside tractor cabin for determining air conditioner vent location
Highlights- Simulation model was developed to evaluate the thermal comfort of agricultural tractor cabin.
AbstractIn this study, thermal comfort was simulated through flow analysis and the air conditioner vent location inside a tractor cabin was determined. The heating test of a tractor in an environmental chamber was performed to obtain ...
Assessment of the Impact of Building Orientation on PMV and PPD in Naturally Ventilated Rooms During Summers in Warm and Humid Climate of Kharagpur, India
BuildSys '23: Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and TransportationThe research focuses on evaluating the impact of door and window orientation on thermal comfort during the summer months. Five different room types (Bedroom and living room) in different buildings, each representing a cardinal orientation and varying ...
Comments