Evaluation of building energy consumption based on fuzzy logic and neural networks applications

The authors have created a Neural-Fuzzy Assistant which acts as a Decision Support System and helps to perform quickly and easily the estimations of office building energy consumption. The Neural-Fuzzy Assistant presented in this paper allows the user to determine the impact of eleven building parameters on the electrical annual and monthly energy consumption, annual and monthly maximum electrical demand and cooling and heating annual consumption and demand. These eleven parameters are : length and width of buildings, number of floors, R-value of exterior wall, fenestration, U-value of windows, windows solar protection, lighting power density, occupancy density, exterior air rate per person and boiler efficiency. The neural networks training and testing data set and fuzzy rules used by the system are based on the simulation results of numerous office buildings. The simulations were carried out with the DOE-2 software program. The accuracy of the Fuzzy Assistant is quite comparable to detailed calculations. The description of the study and the discussion of the obtained results are presented in this paper