摘要
为了提高电力系统短期负荷预测的精度,提出了一种基于马尔科夫模型的组合预测算法。该算法利用双正交小波线性相位的特点,对负荷时间序列进行小波包多分辨分解。针对短时电力负荷具有较强随机波动性,采用软阈值方法检测和处理不良信号,用去噪后的信号建立模糊马尔科夫预测模型,通过将各负荷序列的预测值加以组合得到最终预测结果。经实际算例验证,该算法能有效地提高预测精度,具有良好的抗干扰和容错能力。
A combination forecasting algorithm based on Markov model is proposed to improve the precision of short-term load forecast for power system.The power load time series are decomposed based on wavelet multi-resolution transform using a bi-orthogonal wavelet which has the feature of linear phases.To solve the strong stochastic fluctuation of the short-term load series,a soft-threshold approach is employed to detect and eliminate the noise.Using the de-noised signals,fuzzy Markov forecasting models are constructed and the final prediction results are obtained by combining the forecasting values of each load series.Experimental results show that the proposed method can improve the prediction accuracy,and has good anti-interference and fault tolerance.
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2011年第6期66-70,共5页
Power System Protection and Control
关键词
短期负荷预测
小波变换
小波包分析
软阈值
模糊马尔科夫
short term load forecasting
wavelet transform
wavelet packet analysis
soft-threshold
fuzzy Markov
