Modeling of the space and domestic hot-water heating energy-consumption in the residential sector using neural networks


Aydinalp M. , Ugursal V., Fung A.

APPLIED ENERGY, vol.79, no.2, pp.159-178, 2004 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 79 Issue: 2
  • Publication Date: 2004
  • Doi Number: 10.1016/j.apenergy.2003.12.006
  • Title of Journal : APPLIED ENERGY
  • Page Numbers: pp.159-178

Abstract

Two methods have been used to model residential end-use energy consumption at the national or regional level: the engineering method and the conditional demand-analysis method. It was recently shown that the neural network (NN) method is capable of accurately modeling the behaviours of the appliances, lighting, and space-cooling energy consumption in the residential sector. As a continuation of the work on the use of the NN method for modeling residentialend-use energy-consumption, two NN based energy-consumption models were developed to estimate the space and domestic hot-water heating energyconsumptions in the Canadian residential sector. This paper presents the NN methodology used in developing the models, the accuracy of the predictions, and some sample results.

Two methods have been used to model residential end-use energy consumption at the national or regional level: the engineering method and the conditional demand-analysis method. It was recently shown that the neural network (NN) method is capable of accurately modeling the behaviours of the appliances, lighting, and space-cooling energy consumption in the residential sector. As a continuation of the work on the use of the NN method for modeling residential end-use energy-consumption, two NN based energy-consumption models were developed to estimate the space and domestic hot-water heating energy consumptions in the Canadian residential sector. This paper presents the NN methodology used in developing the models, the accuracy of the predictions, and some sample results. (C) 2004 Elsevier Ltd. All rights reserved.