Real-time data based thermal comfort prediction leading to temperature setpoint control

Abstract

The different thermal comfort indices such as Predictive Mean Vote (PMV), Standard Effective Temperature (SET), and Thermal Sensations (TS) have been used to predict occupants’ thermal comfort in a building. The advances in the machine learning approach help overcome the challenges of predicting current traditional thermal indices in a real-time environment. The different indices have different types of data samples (continuous/labelled). Therefore, while considering the machine learning technique in developing the models of the predictive thermal indices, it is essential to select the vital features, the proper learning type, the algorithm, and the evaluation method to establish the models of the predictive thermal comfort. The main focus of this paper is on the development of the ML model and the evaluation technique that helps in selecting the best model in predicting the thermal indices. This work proposes the new neighbourhood-component-analysis Bayesian-optimization-algorithm-based artificial-neural-network to develop a predictive model for the thermal indices. Here, we have proposed a regression-based model to predict PMV, SET and a classification-based model to predict 7-point TS. The statistical-testing results specify that the ANN model's performance is highly accurate and more reliable in predicting the thermal perception in a real-time environment. The performance of the selected model is validated using subjective measures. This prediction leads to the pre-emptive control of the setpoint temperature of the air-conditioning unit, hence resulting in energy efficiency and comfort.

Digital Twin-Driven Thermal Error Prediction for CNC Machine Tool Spindle

“…Liao et al established a robust thermal error model for spindles based on the improved fruit fly optimization algorithm [8]. Kumar et al designed a real-time LSTM-based predictive model for thermal perception [9]. Li et al established a multiple regression approach, which used nut temperature and ambient temperature as independent variables of the model [10].…”

Data-Driven Smart Avatar for Thermal Comfort Evaluation in Chile

“…In [12], the authors also analyzed thermal comfort in naturally ventilated buildings; however, the predictions were based on machine learning models that showed effective and competitive results. The same strategy was also used by the authors in [7,10] for the estimation of the PMV. The authors of [13] presented a survey on machine learning applications for thermal comfort in which they highlighted the most relevant techniques, metrics, and programming languages used in the thermal comfort field.…”

“…This also implies that limited feedback could be offered to occupants or building operators, which can make it difficult to adjust the indoor environment to improve thermal comfort and energy efficiency [9]. Consequently, advances made with machine learning (ML)-based solutions can help mitigate the shortcomings and challenges faced by traditional comfort models and upgrade them to a real-time environment, thereby adapting to changing environmental conditions and occupant behavior to maintain optimal thermal comfort and energy efficiency [10].…”

Data-Driven Optimisation Based Machine Learning for Thermal Comfort in Building Environment

“…Reinforcement learning based on fuzzy rules is also used by May (2019) to control the Heating, Ventilation, and Air Conditioning (HVAC) setpoint and predict personal comfort. Other studies incorporate machine learning methods to predict thermal comfort as seen in Farhan et al (2015), Chaudhuri et al (2015), Kumar & Kurian (2022), and reinforcement learning, as demonstrated by Gao et al (2020). Based on the predicted thermal comfort, an advisable increase/decrease of the temperature is sent to the controller.…”

“…The first three cases are performed using Algorithm 1 on each of the two classifiers. Referring Kumar & Kurian (2022), case 4 is performed using the PMV equation to predict the thermal comfort, where the temperature setpoint is iteratively adjusted to keep the output in a range of -0.5 to 0.5.…”