Locally recurrent neural networks for long-term wind speed and power prediction

被引:99
作者
Barbounis, TG [1 ]
Theocharis, JB [1 ]
机构
[1] Aristotle Univ Thessaloniki, Dept Elect & Comp Engn, Div Elect & Comp Engn, Thessaloniki 54124, Greece
关键词
local recurrent neural networks; sensitivity networks; recursive prediction error algorithm; local learning algorithms; long-term wind forecasting;
D O I
10.1016/j.neucom.2005.02.003
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The paper deals with a real-world application, the long-term wind speed and power forecasting in a wind farm using locally recurrent multilayer networks as forecast models. To cope with the complexity of the process and to improve the performance of the models, a class of optimal on-line learning algorithms is employed for training the locally recurrent networks based on the recursive prediction error (RPE) algorithm. A global RPE algorithm is devised and three local learning algorithms are suggested by partitioning the GRPE into a set of subproblems at the neuron level to reduce computational complexity and storage requirements. Experimental results on the wind prediction problem demonstrate that the proposed algorithms exhibit enhanced performance, in terms of convergence speed and the accuracy of the attained solutions, compared to conventional gradient-based methods. Furthermore, it is shown that the suggested recurrent forecast models outperform the atmospheric and time-series models. (c) 2005 Elsevier B.V. All rights reserved.
引用
收藏
页码:466 / 496
页数:31
相关论文
共 30 条
  • [1] AKYLAS E, 1999, P EWEC99, P1074
  • [2] [Anonymous], INTERNATIONAL JOINT
  • [3] FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
    Back, A. D.
    Tsoi, A. C.
    [J]. NEURAL COMPUTATION, 1991, 3 (03) : 375 - 385
  • [4] A SIMPLIFIED GRADIENT ALGORITHM FOR IIR SYNAPSE MULTILAYER PERCEPTRONS
    BACK, AD
    TSOI, AC
    [J]. NEURAL COMPUTATION, 1993, 5 (03) : 456 - 462
  • [5] A COMPARISON OF THE BACKPROPAGATION AND RECURSIVE PREDICTION ERROR ALGORITHMS FOR TRAINING NEURAL NETWORKS
    BILLINGS, SA
    JAMALUDDIN, HB
    CHEN, S
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 1991, 5 (03) : 233 - 255
  • [6] Bossanyi E. A., 1985, Wind Engineering, V9, P1
  • [7] On-line learning algorithms for locally recurrent neural networks
    Campolucci, P
    Uncini, A
    Piazza, F
    Rao, BD
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (02): : 253 - 271
  • [8] CAMPOLUCCI P, 1995, P IEEE INT C NEUR NE, P865
  • [9] CAMPOLUCCI P, 1997, P ICASSP 97 MUN GERM, P3293
  • [10] CAMPOLUCCI P, 1996, P IEEE INT S CIRC SY, P531