[1]廖晓辉,周冰,杨冬强,等.一种基于HHT的短期电价组合预测方法[J].郑州大学学报(工学版),2016,37(01):10-14.[doi:10.3969/j.issn.1671-6833.201503041]
 Liao Xiaohui,Zhou Bing,Yang Dongqiang,et al.A Method for Short-term Electricity Price Forecasting Based on HHT[J].Journal of Zhengzhou University (Engineering Science),2016,37(01):10-14.[doi:10.3969/j.issn.1671-6833.201503041]
点击复制

一种基于HHT的短期电价组合预测方法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
37卷
期数:
2016年01期
页码:
10-14
栏目:
出版日期:
2016-02-28

文章信息/Info

Title:
A Method for Short-term Electricity Price Forecasting Based on HHT
作者:
廖晓辉1周冰1杨冬强1武杰2
1.郑州大学 电气工程学院,河南 郑州,450001;2.郑州市供电公司,河南 郑州,450051
Author(s):
Liao Xiaohui1Zhou Bing1Yang Dongqiang1Wu Jie2
1. School of Electrical Engineering, Zhengzhou University, Zhengzhou, Henan, 450001; 2. Zhengzhou Power Supply Company, Zhengzhou, Henan, 450051
关键词:
电力市场电价预测HHT组合预测
Keywords:
power marketelectricity price forecastingHilbert-Huang transformcombined forecasting
DOI:
10.3969/j.issn.1671-6833.201503041
文献标志码:
A
摘要:
短期电价预测保障了电力市场中各参与方的最大效益,针对非平稳非线性的电价序列,提出了一种基于Hilbert-Huang变换的组合预测模型.首先将电价序列进行经验模态分解,得到若干固有模态函数分量及余项,其次根据各分量变化规律分别进行预测,最后将各分量的预测结果相加即为电价预测值.并以美国 PJM ( Pennsylvania-New Jersey-Maryland)电力市场的实际数据进行仿真,将各算法的预测结果进行比较,得出此方法预测精度均高于单一预测模型,其最大绝对误差为1. 53 S|/MWh,平均绝对误差为1. 61%,由此表明,该模型具有较高的预测精度.
Abstract:
Short-term electricity price forecasting guarantees the maximum benefit of the parties involved in the power market. In view of the fact that the market clearing price has strong randomness and volatility, the paper proposes a combination forecasting model based on Hilbert-Huang transform. The price sequence is decom-posed into a number of intrinsic mode function components and the remainder by using the empirical mode de-composition theory. Different models were built for each intrinsic mode function according to the size of each component’ s average instantaneous frequency. Then the prediction results of each component are added up to obtain the final prediction value. And the model uses the actual data of PJM power market in the United States to test. Compared to the prediction results of any one sole model, this method accuracy were higher than single forecasting model, the maximum absolute error is 1. 53 S|/MWh and the mean absolute percentage error is 1. 61.
更新日期/Last Update: