Prediction of building energy needs in early stage of design by using ANFIS

Studies performed on the prediction of building energy consumption are increasingly important for selecting the best control strategies against the excessive energy consumptions. This paper presents Adaptive Network Based Inference System (ANFIS) model to forecast building energy consumption in a cold region. The objective of this paper is to examine the feasibility and applicability of ANFIS in building energy load forecasting area. Different combinations of building samples formed by using three different form factors (FF 1/2, FF 1/1 and FF 2/1), nine azimuth angles varied 0 degrees-80 degrees, three transparency ratios of 15%, 20%, 25% and five insulation thicknesses of 0, 2.5, 5, 10 and 15 cm. Finally, it is observed that ANFIS can be a strong tool with the 96.5 and 83.8% for heating and cooling energy prediction in pre-design stage of energy efficient buildings for choosing the best combinations. (C) 2010 Elsevier Ltd. All rights reserved.