Inference of thermal preference profiles for personalized thermal environments with actual building occupants

Lee, Seungjae; Karava, Panagiota; Tzempelikos, Athanasios; Bilionis, Ilias

doi:10.1016/j.buildenv.2018.10.027

Cited by 68 publications

(22 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bayesian inference [123], [124] Home appliances scheduling RL: value based [125] Heat pump operation RL: value based [126]…”

Section: Machine Learning For Building Controlmentioning

confidence: 99%

“…Blum et al (2019) [96] applied this approach in his study: given an acceptable temperature range, the energy consumption is minimized. The comfort range, i.e., the lower and upper bound of temperature , and , might come from current standards, statistical analysis on a large open-source database [123], or directly from building users' votes [124]. Similarly, the multi-objective optimization problem could be formulated as enforcing the energy consumption as a hard constraint while maximizing the comfort benefit, which could be interpreted as: given the energy consumption budget, the occupants' comfort is maximized.…”

Section: Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

250

View full text Add to dashboard Cite

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

show abstract

“…Bayesian inference [123], [124] Home appliances scheduling RL: value based [125] Heat pump operation RL: value based [126]…”

Section: Machine Learning For Building Controlmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

250

View full text Add to dashboard Cite

show abstract

“…Under the context of this study, the Bayesian Inference provides a useful and powerful tool to quantify occupants' thermal adaptive behaviors and inter-individual variabilities in thermal comfort demands, both of which need to be taken into account in selecting comfort temperature. Additionally, Bayesian approach can easily account for hidden variables [36] such as metabolic rate, clothing, individualized preference [37], which are difficult to measure but important in thermal comfort studies. Thirdly, Bayesian Inference facilitates active learning, allowing the controller to update the set-point based on new observations.…”

Section: Bayesian Inference 241 Motivationmentioning

confidence: 99%

“…Then, Bayesian Inference was applied to predict the thermal preference of each cluster based on environmental and behavioral parameters [38]. Bayesian approach has also been used to account for the modeling uncertainty associated with difficult-to-measure variables [37]. Langevin et al applied Bayesian approach to predict thermal sensation, acceptability, and preference based on PMV value [39].…”

Section: Literature Reviewmentioning

confidence: 99%

Learning occupants’ indoor comfort temperature through a Bayesian inference approach for office buildings in United States

Wang

Hong

2020

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

A carefully chosen indoor comfort temperature as the thermostat set-point is the key to optimizing building energy use and occupants' comfort and well-being. ASHRAE Standard 55 or ISO Standard 7730 uses the PMV-PPD model or the adaptive comfort model that is based on small-sized or outdated sample data, which raises questions on whether and how ranges of occupant thermal comfort temperature should be revised using more recent larger-sized dataset. In this paper, a Bayesian inference approach has been used to derive new occupant comfort temperature ranges for U.S. office buildings using the ASHRAE Global Thermal Comfort Database. Bayesian inference can express uncertainty and incorporate prior knowledge. The comfort temperatures were found to be higher and less variable at cooling mode than at heating mode, and with significant overlapped variation ranges between the two modes. The comfort operative temperature of occupants varies between 21.9 and 25.4°C for the cooling mode with a median of 23.7°C, and between 20.5 and 24.9°C for the heating mode with a median of 22.7°C. These comfort temperature ranges are similar to the current ASHRAE standard 55 in the heating mode but 2-3°C lower in the cooling mode. The results of this study could be adopted as more realistic thermostat set-points in building design, operation, control optimization, energy performance analysis, and policymaking.

show abstract

“…On the contrary, Gao and Keshav [64] Predicted Personal Vote (PPV) model to individualise thermal comfort based on thermal preference of the occupants. Lee et al [65] introduced the Personalised Preference Model, which is mainly based on the three point thermal preference scale, environmental factors (i.e. air temperature, relative humidity, air velocity, and mean radiant temperature) and personal factors (i.e.…”

Section: Individual Differences In Perceiving the Thermal Environmentmentioning

confidence: 99%

Patterns of thermal preference and Visual Thermal Landscaping model in the workplace

et al. 2019

View full text Add to dashboard Cite

The main purpose of research on occupant behaviour is to enhance building energy performance. However, it is difficult to reduce the energy use without understanding the occupant, their needs and preferences. Individual differences and preferences for the thermal environment in relation to the spatial context are overlooked in the main stream of research. This study investigates the patterns of occupant thermal preference based on individual differences in perceiving the thermal environment to enhance user comfort and energy performance. A novel method of Visual Thermal Landscaping is used, which is a qualitative method to analyse occupant comfort and user behaviour according to the spatial context. This method drives away from the notion of 'thermal neutrality' and generic results, rather it opens to details and meaning through a qualitative analysis of personal-comfort, based on individual differences and spatial context information. Field test studies of thermal comfort were applied in five office buildings in the UK, Sweden and Japan with overall 2,313 data sets. The primary contribution of the study was the recognition of four patterns of thermal preference, including consistent directional preference; fluctuating preference; high tolerance and sensitive to thermal changes; and high tolerance and not-sensitive to thermal changes. The results were further examined in a longitudinal field test study of thermal comfort. In several cases, occupant thermal comfort and preferences were observed to be influenced by the impact of outdoor conditions, when the windows were fixed. Practical solutions for research, practice and building design were recommended with direct implications on occupant comfort and energy use.

show abstract

Inference of thermal preference profiles for personalized thermal environments with actual building occupants

Cited by 68 publications

References 36 publications

State-of-the-art on research and applications of machine learning in the building life cycle

State-of-the-art on research and applications of machine learning in the building life cycle

Learning occupants’ indoor comfort temperature through a Bayesian inference approach for office buildings in United States

Patterns of thermal preference and Visual Thermal Landscaping model in the workplace

Contact Info

Product

Resources

About