Model behaviour of cooling plant using subtractive clustering ANFIS at university buildings

Abstract

The chiller that is used to provide cooling for buildings consumes high power, especially if not optimally operated. Thus, the use of demand response (DR); it is an important aspect of demand side management can be employed to reduce power consumption. This paper proposes cooling models to solve the complexity of chillers behavior at the demand-side using a hybrid technique. A hybrid technique of subtractive clustering adaptive neuro-fuzzy inference system (SC-ANFIS) is used to construct the model according to real operating data to manage and control the chillers cooling behavior. The obtained results demonstrate the SCANFIS improve system performance, tune the cooling temperature, and reduces energy consumption. The SC-ANFIS is validated with gas district cooling operating in UniversitiTeknologi PETRONAS

Keywords: Cooling Models, Subtractive Clustering (SC), Adaptive System (ANFIS)