Optimal Heating Load Identification using a DRNN

DRNN을 이용한 최적 난방부하 식별

  • Published : 1999.10.01

Abstract

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

Keywords

References

  1. 제어계측 자동화 로보틱스 연구회 합동 학술회의 신경회로망을 이용한 최적난방 부하예측 앨고리즘 개발 김동헌;양해원;최병윤;주용진;이경호
  2. ASHRAE Transactions v.100 no.2 Artificial neural network backpropagation model with three-phase annealing developed of the building energy predictor shoot-out Kawashima, M.
  3. IEEE Trans. Neural Networks v.1 no.1 Idetification and Control of Dynamical Systems Using Neural Networks K.S. Narendra;K. Parthasarathy
  4. Proc. 1992 American Control Conf. System identification and control using diagonal recurrent neural networks C. C. Ku;K. Y. Lee
  5. ASHRAE Transaction : Research v.101 A Modeling of An Environmental Chamber A. Kimbra(et al.)
  6. Fundamentals of Neural Networks L. Fausett
  7. IEEE Trans. on Power Systems v.11 no.2 A Neural Network Short Term Load Forecasting Model for the Greek Power System A. G. Baklrtzls;V. Petrldls;S. J. Klartzls;M. C. Alexladls
  8. ASHRAE Transactions : Research Hourly thermal load prediction for the next 24hours by ARIMA, EWMA, LR, and an artificial neural network M. Kawashima;C. E. Dorgan;John W. Mitchell