Improve the Control of Residential Heating Systems

A recurrent neuro-fuzzy based inferential sensor is applied to design an inferential control algorithm that can improve the operation of residential heating systems in which both energy efficiency and indoor environment quality are below expectation due to insufficient control. In current practice, the control of these heating systems is based on the measurement of air temperature at one point within the building. The inferential control strategy presented in this paper allows the control to be based on an estimate of the overall thermal performance, minimizing the chance of overheating (saving energy) and underheating (improving comfort) in the building. The performance of this control technology has been investigated through simulation study. The results show that the proposed control scheme can effectively maintain the temperature at set-point, and results in energy savings and improved thermal comfort.