[1]杨小强,韩亚军,刘 静.几种短期风速时间序列预测技术的比较[J].常州大学学报(自然科学版),2016,(01):88-92.[doi:10.3969/j.issn.2095-0411.2016.01.017]
　YANG Xiaoqiang,HAN Yajun,LIU Jing.A Comparison of Various Forecasting Techniques Applied to Mean Hourly Wind Speed Time Series[J].Journal of Changzhou University(Natural Science Edition),2016,(01):88-92.[doi:10.3969/j.issn.2095-0411.2016.01.017]
点击复制

几种短期风速时间序列预测技术的比较()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
期数:
2016年01期
页码:
88-92
栏目:
出版日期:
2016-01-28

文章信息/Info

Title:
A Comparison of Various Forecasting Techniques Applied to Mean Hourly Wind Speed Time Series
文章编号:
2095-0411(2016)01-0088-05
作者:
杨小强; 韩亚军; 刘 静
重庆科创职业学院 机电工程学院,重庆 402160
Author(s):
YANG Xiaoqiang; HAN Yajun; LIU Jing
School of Machine and Electrical Engineering, Chongqing Creation Vocational College, Chongqing 402160, China
关键词:
风速;  时间序列;  神经网络
Keywords:
wind speed;  time series;  neural networks
分类号:
TM 614
DOI:
10.3969/j.issn.2095-0411.2016.01.017
文献标志码:
A
摘要:
对风速进行准确的预测可以减轻对电力系统的不利影响,提高风电场在电力市场中的竞争力。比较了几种不同的风速预测方法,它们都是采用时间序列分析短期风速数据。讨论传统的线性自回归滑动平均模型(ARMA),常用的前馈和循环神经网络,同时对自适应神经模糊推理系统(ANFIS)以及神经逻辑网络进行比较。通过建模对几种方法的预测性能进行估计,最终得出基于人工智能的模型比线性模型效果更好,能够准确快速地预测结果。
Abstract:
Accurate prediction wind speed can reduce the iMPact on the power system and improve the competitiveness of the wind farm in the electric power market.This paper mainly compared several different wind speed forecasting methods, which use the time series to analyze the short-term wind speed data,discussed the traditional linear auto regressive moving average model(ARMA),the common feed forward and recurrent neural network,and also compared the adaptive neural fuzzy inference system(ANFIS)and the neural logic network.The model shows that the artificial intelligence model is better than the linear model,and it can predict the wind speed accurately and quickly.

参考文献/References:

[1]曾勇红,王锡凡,冯宗建.基于混合自回归滑动平均潜周期模型的短期电价预测[J].西安交通大学学报,2008,42(2):34-38.
[2]李士勇.模糊控制.神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学,1996:250-387.
[3]WATSON S, HALLIDAY J A, LANDBERG L. Wind speed forecasting and its application to wind powerintegration[J].Proceedings of the Fifteenth British Wind Energy Association Conference,1993,35(12):61-70.
[4]王凤琴,高颖,赵军.基于遗传算法的神经网络优化[J].燕山大学学报,2001,18(3):21-26
[5]邵红梅,安凤仙.一类训练前馈神经网络的梯度算法及收敛性[J].中国石油大学学报(自然科学版),2010,34(4):89-93.
[6]贾立山,谈至明.基于随机参数调整的改进反向传播学习算法[J].同济大学学报(自然科学版),2011,39(5):57-62.
[7]郝欢,陈亮,张翼鹏.采用归一化最小均方误差准则的LM-BP算法[J].信号处理,2013,29(8):193-197.
[8]CONNOR J, MARTIN R, ATLAS L. Recurrent neural Networks and robust time series prediction[J]. IEEE Trans Neural Networks,1994,5(2):240-253.

相似文献/References:

[1]邵?? 辉,李志刚,吕培林,等.火灾经济损失时间序列分析[J].常州大学学报(自然科学版),2009,(04):56.
　SHAO Hui,LI Zhi- g ang,LV Pei- lin,et al.Time Series Analysis in Fire Economic Loss[J].Journal of Changzhou University(Natural Science Edition),2009,(01):56.
[2]王凯全,程志斌.南京炼油厂生活区恶臭污染规律分析[J].常州大学学报(自然科学版),2006,(04):21.
　WANG Kai-quan,CHENG Zhi -bin.Analysis of Odor Pollution Law in the Living Area of Nanjing Refinery Plant[J].Journal of Changzhou University(Natural Science Edition),2006,(01):21.

备注/Memo

备注/Memo:
基金项目:重庆市第二批高等学校青年骨干教师资助计划(渝教人〔2013〕74号)。作者简介:杨小强(1983—),男,甘肃天水人,助教,主要从事电气工程及自动化教学研究。
更新日期/Last Update: 2016-01-28