More Like this

1. Data-driven modeling of dynamic occupant thermostat override behavior for demand response applications

   Sharma, Kunind (April 2025, Northeastern University)

   Buildings consume nearly 40% of global energy and produce similar emissions. Whiletechnological advances address efficiency, occupant behavior causes energy use variations up to 300% between identical buildings. This gap between predicted and actual building performance impacts building design, operations, and grid demand management programs. Through analyses of smart thermostat data from 1,400 single-occupant homes, the researchdemonstrates that occupants respond to 8°F thermostat setpoint changes within a median of 15 minutes, while 2°F changes trigger responses within a median of 30 minutes. This highlights an understudied temporal relationship between thermostat setbacks and response time of occupant behaviors. Models of such behavior dynamics are required to incorporate occupant impacts into building performance simulation. A key contribution of this dissertation is the Thermal Frustration Theory (TFT), which positsthat thermal discomfort driven behaviors are caused by the time-accumulation of discomfort, not simply a temperature deviation threshold or a delay from an initiating event. Using a dataset of 634 thermostats, each with 25+ manual setpoint changes, a comparative analysis of TFT and comfort zone and a delayed response theories demonstrated that personalized TFT models better predict when manual setpoint change occur. This was measured by the area under the curve statistical measure (AUC); all three models perform similarly by a Matthews Correlation Coefficient measure. Higher AUC performance is especially important for modeling occupant behavior in demand response programs where false negatives of rare occupant interactions could adversely affect grid stability. EnergyPlus based simulations were conducted with TFT-derived occupant models, demonstrating the ability to identify parameters of known TFT models from only data observable with smart thermostats, even under the presence of noise from routine overrides. Overall, the dissertation highlights that thermostat interactions are neither static,instantaneous, nor driven solely by the environment. Instead, temporal accumulation of discomfort and routine-based behavior play important roles. The methodology and results offer a pathway towards more accurate modeling of human-building interactions for policy assessment, building design, and demand response programs. 

   more » « less
2. Investigating Receptivity and Affect Using Machine Learning: Ecological Momentary Assessment and Wearable Sensing Study

   https://doi.org/10.2196/46347  

   King, Zachary D; Yu, Han; Vaessen, Thomas; Myin-Germeys, Inez; Sano, Akane (January 2024, JMIR mHealth and uHealth)

   BackgroundAs mobile health (mHealth) studies become increasingly productive owing to the advancements in wearable and mobile sensor technology, our ability to monitor and model human behavior will be constrained by participant receptivity. Many health constructs are dependent on subjective responses, and without such responses, researchers are left with little to no ground truth to accompany our ever-growing biobehavioral data. This issue can significantly impact the quality of a study, particularly for populations known to exhibit lower compliance rates. To address this challenge, researchers have proposed innovative approaches that use machine learning (ML) and sensor data to modify the timing and delivery of surveys. However, an overarching concern is the potential introduction of biases or unintended influences on participants’ responses when implementing new survey delivery methods. ObjectiveThis study aims to demonstrate the potential impact of an ML-based ecological momentary assessment (EMA) delivery system (using receptivity as the predictor variable) on the participants’ reported emotional state. We examine the factors that affect participants’ receptivity to EMAs in a 10-day wearable and EMA–based emotional state–sensing mHealth study. We study the physiological relationships indicative of receptivity and affect while also analyzing the interaction between the 2 constructs. MethodsWe collected data from 45 healthy participants wearing 2 devices measuring electrodermal activity, accelerometer, electrocardiography, and skin temperature while answering 10 EMAs daily, containing questions about perceived mood. Owing to the nature of our constructs, we can only obtain ground truth measures for both affect and receptivity during responses. Therefore, we used unsupervised and supervised ML methods to infer affect when a participant did not respond. Our unsupervised method used k-means clustering to determine the relationship between physiology and receptivity and then inferred the emotional state during nonresponses. For the supervised learning method, we primarily used random forest and neural networks to predict the affect of unlabeled data points as well as receptivity. ResultsOur findings showed that using a receptivity model to trigger EMAs decreased the reported negative affect by >3 points or 0.29 SDs in our self-reported affect measure, scored between 13 and 91. The findings also showed a bimodal distribution of our predicted affect during nonresponses. This indicates that this system initiates EMAs more commonly during states of higher positive emotions. ConclusionsOur results showed a clear relationship between affect and receptivity. This relationship can affect the efficacy of an mHealth study, particularly those that use an ML algorithm to trigger EMAs. Therefore, we propose that future work should focus on a smart trigger that promotes EMA receptivity without influencing affect during sampled time points. 

   more » « less
3. Variable and dynamic associations between hot weather, thermal comfort, and individuals’ emotional states during summertime

   https://doi.org/10.1186/s40359-024-02005-z  

   Meidenbauer, Kimberly_L; Schertz, Kathryn_E; Li, Peiyuan; Sharma, Ashish; Freeman, Tiara_R; Janey, Elizabeth_A; Stier, Andrew_J; Samtani, Anya_L; Gehrke, Kathryn; Berman, Marc_G (September 2024, BMC Psychology)

   Abstract The effects of heat exposure on negative affect are thought to be central to the observed relationships between hot summer days and deleterious outcomes, such as violent crime or mental health crises. As these relationships are likely to be magnified by the effects of climate change, a better understanding of how consistent or variable the effects of hot weather on affective states is required. The current work combines data gathered from an ecological momentary assessment (EMA) study on individuals’ thermal perceptions, comfort, and affective states in outdoor environments during their daily lives with high spatiotemporal resolution climate-modeled weather variables. Using these data, associations between objective weather variables (temperature, humidity, etc.), perceived heat (thermal perception and comfort), and affective states are examined. Overall, objective weather data reasonably predicted perception and comfort, but only comfort predicted negative affective states. The variance explained across individuals was generally very low in predicting negative affect or comfort, but within-person variance explained was high. In other words, while there may be a relatively consistent relationship between temperature and psychological experience for any given person, there are significant individual differences across people. Age and gender were examined as moderators of these relationships, and while gender had no impact, participant age showed several significant interactions. Specifically, while older adults tended to experience more thermal discomfort and perceived higher temperatures as hotter, the relationship between discomfort and negative affect was lower in older adults. Taken together, these results emphasize the importance of thermal discomfort specifically in predicting negative affect, as well as the high inter-individual variability in thermal perceptions and comfort for the same ambient temperatures. 

   more » « less
4. Enhancing HVAC energy management through multi-zone occupant-centric approach: A multi-agent deep reinforcement learning solution

   https://doi.org/10.1016/j.enbuild.2023.113770  

   Liu, Xuebo; Wu, Yingying; Wu, Hongyu (January 2024, Energy and Buildings)

   Occupant-centric HVAC control places a premium on factors including thermal comfort and electricity cost to guarantee occupant satisfaction. Traditional approaches, reliant on static models for occupant behaviors, fall short in capturing intra-day behavioral variations, resulting in imprecise thermal comfort evaluations and suboptimal HVAC energy management, especially in multi-zone systems with diverse occupant profiles. To address this issue, this paper proposes a novel occupant-centric multi-zone HVAC control approach that intelligently schedules cooling and heating setpoints using Multi-agent Deep Reinforcement Learning (MADRL). This approach systematically takes into account stochastic occupant behavior models, such as dynamic clothing insulation adjustments, metabolic rates, and occupancy patterns. Simulation results demonstrate the efficacy of the proposed approach. Comparative case studies show that the proposed MADRL-based, occupant-centric HVAC control reduces electricity costs by 51.09% compared to rule-based approaches and 4.34% compared to single-agent DRL while maintaining multi-zonal thermal comfort for occupants. 

   more » « less
5. Meta-learning of personalized thermal comfort model and fast identification of the best personalized thermal environmental conditions

   https://doi.org/10.1016/j.buildenv.2023.110201  

   Chen, Liangliang; Ermis, Ayca; Meng, Fei; Zhang, Ying (May 2023, Building and Environment)

   The model of personalized thermal comfort can be learned via various machine learning algorithms and used to improve the individuals’ thermal comfort levels with potentially less energy consumption of HVAC systems. However, the learning of such a model typically requires a substantial number of thermal votes from the considered occupant, and the environmental conditions needed for collecting some votes may be undesired by the occupant in order to obtain a model with good generalization ability. In this paper, we propose to use a meta-learning algorithm to reduce the required number of personalized thermal votes so that a personalized thermal comfort model can be obtained with only a small number of feedback. With the learned meta-model, we derive a method based on the backpropagation of neural networks to quickly identify the best environmental and personal conditions for a specific occupant. The proposed identification algorithm has an additional advantage that the thermal comfort, indicated by the mean thermal sensation value, improves incrementally during the data collection process. We use the ASHRAE global thermal comfort database II to verify that the meta-learning algorithm can achieve an improved prediction accuracy after using 5 thermal sensation votes from an occupant to make adaptations. In addition, we show the effectiveness of the fast identification algorithm for the best personalized thermal environmental conditions with a thermal sensation generation model built from the PMV model. 

   more » « less