Automatic Control System Based on Predicted Mean Vote and Energy Saving for Thermal Comfort

For human-centered automation, this study presents a wireless sensor network using predicted mean vote (PMV) as a thermal comfort index around occupants in buildings. The network automatically controls air conditioning by means of changing temperature settings in air conditioners. Interior devices of air con-ditioners thus do not have to be replaced. An adaptive neurofuzzy inference system and a particle swarm algorithm are adopted for solving a nonlinear multivariable inverse PMV model so as to de-termine thermal comfort temperatures. In solving inverse PMV models, the particle swarm algorithm is more accurate than ANFIS according to computational results. Based on the comfort temper-ature, this study utilizes feedforward– feedback control and digital self-tuning control, respectively, to satisfy thermal comfort. The control methods are validated by experimental results. Compared with conventional fi xed temperature settings, the present control methods effectively maintain the PMV value within the range of and energy is saved more than 30% in this study. Note to Practitioners—For advanced control of unitary air conditioners in rooms, air conditioners may have to be retrofitted or con-nected with extra devices by wire connection, whose processes may be difficult for users, and inappropriate installation may damage original air-conditioning units. This study hence presents a nonin-vasive method for indoor thermal comfort with a wireless sensor network. The present method facilitates hardware implementation without changing interior devices of the air conditioner. The wire-less sensor network measures temperature, air velocity, and hu-midity around occupants and further transmits temperature com-mands for air conditioner control. Based on the measured data, a PMV model is adopted to evaluate thermal comfort. Using an inverse PMV model with feedforward– feedback control and self-tuning control, respectively, this study aims to automatically main-tain human thermal comfort as well as save energy. The ANFIS model and a particle swarm algorithm are used to solve the in-verse PMV model and determine the thermal comfort tempera-ture. Based on that temperature, feedforward–feedback control, and self-tuning control are used to determine appropriate temper-ature settings in the air conditioner so as to change the cooling ca-pacity and maintain thermal comfort. Experimental results show that the present control method can maintain thermal comfort and saves 30% more energy than the conventional method. Index Terms – Adaptive neurofuzzy inference system, automatic air conditioning control, particle swarm algorithm, predicted mean vote (PMV), self-tuning control.