Modeling of the appliance, lighting, and space-cooling energy consumptions in the residential sector using neural networks


Aydinalp M., Ugursal V., Fung A.

APPLIED ENERGY, cilt.71, sa.2, ss.87-110, 2002 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 71 Sayı: 2
  • Basım Tarihi: 2002
  • Doi Numarası: 10.1016/s0306-2619(01)00049-6
  • Dergi Adı: APPLIED ENERGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.87-110
  • Anahtar Kelimeler: residential energy consumption modeling, appliance, lighting, and space-cooling energy, neural networks modeling, CONDITIONAL-DEMAND, FUEL SUBSTITUTION, CANADA, EFFICIENCY, IMPACT
  • Hacettepe Üniversitesi Adresli: Hayır

Özet

Two methods are currently used to model residential energy consumption at the national or regional level: the engineering method and the conditional demand analysis method. Another potentially feasible method to model residential energy consumption is the neural network (NN) method. Using the NN method, it is possible to determine causal relationships amongst a large number of parameters. such as occur in the energy consumption patterns in the residential sector. A review of the published literature indicates that the NN method has not been used or tested for housing-sector energy consumption modeling. A NN based energy consumption model is being developed for the Canadian residential sector. This paper presents the NN methodology used in developing the appliances, lighting, and space-cooling component of the model, the accuracy of its predictions, and some sample results. (C) 2002 Elsevier Science Ltd. All rights reserved.

Two methods are currently used to model residential energy consumption at the national or regional level: the engineering method and the conditional demand analysis method. Another potentially feasible method to model residential energy consumption is the neural network (NN) method. Using the NN method, it is possible to determine causal relationships amongst a large number of parameters. such as occur in the energy consumption patterns in the residential sector. A review of the published literature indicates that the NN method has not been used or tested for housing-sector energy consumption modeling. A NN based energy consumption model is being developed for the Canadian residential sector. This paper presents the NN methodology used in developing the appliances, lighting, and space-cooling component of the model, the accuracy of its predictions, and some sample results.