Title :
Energy-efficient operation of HVAC systems using neural network based decentralized controllers
Author :
Saboksayr, S.H. ; Patel, R.V. ; Zaheer-Uddin, M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Concordia Univ., Montreal, Que., Canada
Abstract :
The authors have designed a neural network based decentralized controller to improve the operation of a multizone space heating (MZSH) system. Two important operational issues are considered: disturbance rejection and occupied/unoccupied setpoint control. The neural network controller is trained to accomplish these tasks efficiently. Results are compared with a robust decentralized controller to show performance improvements
Keywords :
HVAC; decentralised control; minimisation; neurocontrollers; nonlinear control systems; servomechanisms; space heating; temperature control; HVAC systems; disturbance rejection; energy-efficient operation; multizone space heating system; neural network based decentralized controllers; occupied/unoccupied setpoint control; robust decentralized controller; Boilers; Centralized control; Control systems; Energy efficiency; Heat pumps; Humidity control; Neural networks; Robust control; Space heating; Temperature control;
Conference_Titel :
American Control Conference, Proceedings of the 1995
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2445-5
DOI :
10.1109/ACC.1995.532750
