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