Modelling of residential energy consumption at the national level

Three methods are currently used to model residential energy consumption at the national level: the engineering method (EM), the conditional demand analysis (CDA) method, and the neural network (NN) method. While the use of the first two methods has been established over the past decade for residential energy modelling, the use of NN method is still in the development and verification phase. The EM involves developing a housing database representative of the national housing stock and estimating the energy consumption of the dwellings in the database using a building energy simulation program. CDA is a regression-based method in which the regression attributes consumption to end-uses on the basis of the total household energy consumption. The NN method models the residential energy consumption as a neural network, which is an information-processing model inspired by the way the densely interconnected, parallel structure of the brain processes information. In this paper, the three methods are briefly described and a comparative assessment of the three methods is presented. Copyright © 2003 John Wiley & Sons, Ltd.

[1]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1993 .

[2]  Kenneth Train.  An assessment of the accuracy of statistically adjusted engineering (SAE) models of end-use load curves , 1992 .

[3]  V. I. Ugursal,et al.  A residential end‐use energy consumption model for Canada , 1998 .

[4]  Moncef Krarti,et al.  Estimation of energy savings for building retrofits using neural networks , 1998 .

[5]  D. Perron,et al.  Evolution of Residential Electricity Demand by End-Use in Quebec 1979-1989: A Conditional Demand Analysis , 1994 .

[6]  D. Aigner,et al.  Conditional Demand Analysis for Estimating Residential End-Use Load Profiles , 1984 .

[7]  J. C. Hwang,et al.  The application of artificial neural networks to substation load forecasting , 1996 .

[8]  Cheng Hsiao,et al.  A Bayesian Integration of End-Use Metering and Conditional-Demand Analysis , 1995 .

[9]  K. Train,et al.  A Bayesian Approach to Combining Conditional Demand and Engineering Models of Electricity Usage , 1987 .

[10]  V. Ismet Ugursal,et al.  Impact of appliance efficiency and fuel substitution on residential end-use energy consumption in Canada , 1996 .

[11]  Denzil G. Fiebig,et al.  A random coefficient approach to the estimation of residential end-use load profiles , 1991 .

[12]  P. J. Werbos,et al.  Backpropagation: past and future , 1988, IEEE 1988 International Conference on Neural Networks.

[13]  George G. Karady,et al.  Advancement in the application of neural networks for short-term load forecasting , 1992 .

[14]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[15]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[16]  S. J. Kiartzis,et al.  Short-term load forecasting using neural networks , 1995 .

[17]  M. Parti,et al.  The Total and Appliance-Specific Conditional Demand for Electricity in the Household Sector , 1980 .

[18]  V. Ismet Ugursal,et al.  Residential carbon dioxide emissions in Canada: Impact of efficiency improvements and fuel substitution , 1998 .

[19]  Magdi S. Mahmoud,et al.  Cascaded artificial neural networks for short-term load forecasting , 1997 .