A comparison of various forecasting techniques applied to mean hourly wind speed time series

被引：297

作者：

Sfetsos, A

机构：

[1] 7 Pirsou Street, 10441, Athens

来源：

RENEWABLE ENERGY | 2000年 / 21卷 / 01期

关键词：

wind speed; time series; forecasting; neural networks;

D O I：

10.1016/S0960-1481(99)00125-1

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

This paper presents a comparison of various forecasting approaches, using time series analysis, on mean hourly wind speed data. In addition to the traditional linear (ARMA) models and the commonly used feed forward and recurrent neural networks, other approaches are also examined including the Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Neural Logic Networks. The developed models are evaluated for their ability to produce accurate and fast forecasts. (C) 2000 Elsevier Science Ltd. All rights reserved.

引用

页码：23 / 35

页数：13

共 26 条

[1] Short-term forecasting of wind speed and related electrical power [J].

Alexiadis, MC ;

Dikopoulos, PS ;

Sahsamanoglou, HS ;

Manousaridis, IM .

SOLAR ENERGY, 1998, 63 (01) :61-68

[2]

[Anonymous], 1996, P 1996 EUR WIND ENER

[3]

Balouktsis A., 1986, Wind Engineering, V10, P1

[4]

Beyer HG., 1994, P 2 EUR C INT TECHN

[5]

Bossanyi E. A., 1985, Wind Engineering, V9, P1

[6]

Box J., 1976, TIME SERIES ANAL

[7]

Chernichow T, 1996, ENG INTELL SYST ELEC, V2, P85

[8] RECURRENT NEURAL NETWORKS AND ROBUST TIME-SERIES PREDICTION [J].

CONNOR, JT ;

MARTIN, RD ;

ATLAS, LE .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :240-254

[9]

*ELSAM, 1993, JOU2CT920083 ELSAM E

[10] TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM [J].

HAGAN, MT ;

MENHAJ, MB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06) :989-993

← 1 2 3 →