Evaluation of energy-saving potential for optimal time response of HVAC control system in smart buildings.

• A novel integrated two different types to control a large-scale nonlinear system. • Converting Takagi-Sugeno fuzzy inference system into faster hybrid layers structure. • Spans of the fuzzy membership functions are tuned on-line to achieved energy saving. • Online tuning by downhill simplex algorithm achieved minimum time response. • Integrated control deal with plants possess lag time, big inertia and uncertainty. In some fields, such as the semiconductor manufacturing process, museum, pharmaceutical, and medicine manufacturing industry, the HVAC system needs a very fast response time to protect products and more energy-efficient buildings than traditional controllers. So, the proposed controller is designed to overcome such problems by using integrated fuzzy PI-PD Mamdani-type (FPIPDM) and cluster adaptive training based on Takagi-Sugeno-Kang (CABTSK) type. The spans of the fuzzy membership functions of the FPIPDM are tuned online by the Nelder-Mead simplex search (NMSS) algorithm to minimize time response, while the CABTSK model is tuned offline and online using a gradient descent (GD) algorithm to enhance the stability of the overall system and reject disturbances. Then, the integration framework is used to enable the concept of time-optimal based on the bang-bang code delegation. In this sense, a selected switch delegates the execution of proper control code to the action processor that provides computational resources to control indoor conditions. The predicted mean vote (PMV) index provides a higher comfort level than the temperature, as it considers six variables related to thermal comfort. The results of the proposed structure show that it improves the overall output accuracy and significantly reduces the response time. Furthermore, it increases the robustness of the indoor conditions and it is quite applicable to the MIMO HVAC systems processes with strong coupling actions between temperature and humidity, large time delay, noise, disturbances, nonlinearities, and imprecise identification model. [ABSTRACT FROM AUTHOR]