基于近似熵的电力系统负荷预测误差分析

Study of power system load forecasting errors based on approximate entropy

为深入探究负荷时间序列预测误差的影响因素,提高负荷预测精度,提出近似熵算法,用于定量刻画负荷时间序列的规律性,全面认识负荷预测误差的成因。采用近似熵算法对负荷时间序列进行分析,确定其规律性的强弱。在此基础上,针对负荷时间序列的规律性与预测误差之间的关系进行研究。算例分析结果表明,近似熵算法可以有效刻画负荷时间序列的规律性,且负荷时间序列的规律性与其预测误差之间有着较强的相关性,证明了方法的正确性和有效性。

To further explore the influence factors of load time sequence forecasting errors and improve the accuracy of load forecasting, an approximate entropy algorithm is proposed for characterizing the regularity of load time series quantitatively and recognizing the causes for load forecasting errors fully. Approximate entropy algorithm is applied to analyze load time series and determine the regularity of it. Based on the above research, this paper carries out the related research according to the relationship between the regularity and forecasting errors of load time series. The results show that, approximate entropy algorithm can describe the regularity of load time series effectively, and there is a strong correlation between regularity of load time series and load forecasting errors, proving the correctness and validity of the method.