摘要
受到温度情况、休息日、甚至突发事件等不确定因素的影响,配电网短期负荷分析准确性不高,与实际情况存在较大的偏差。针对上述问题,提出一种基于经验模态分解与偏差校正的配电网短期负荷水平分析方法。对配电网负荷数据进行预处理,包括缺失数据弥补、异常值处理以及归一化;利用经验模态分解,将预处理好的配电网负荷时间序列分解为若干独立IFM分量,以这些独立IFM分量为输入,利用深度置信网络分析配电网短期负荷值。引入模糊控制方法,将温度变化及休息日这两种常见的不确定因素考虑在内,优化深度置信网络计算得出的基本短期负荷分析结果,实现偏差校正。试验结果表明:所研究方法应用下,配电网短期负荷水平分析结果与实际结果之间的偏差均有所降低,尤其周六日,达到了研究目标,说明配电网短期负荷水平分析精度有所提高。
Because of uncertain factors such as temperature,weekends and even emergencies,the accuracy of distribution network short-term load analysis is not ideal,and there is a large deviation from the actual situation.Aiming at the problem,a distribution network short-term load level analysis method based on empirical mode decomposition and deviation correction is proposed.We preprocess the load data of distribution network,including missing data compensation,abnormal value processing and normalization.Then,using empirical mode decomposition,the preprocessed distribution network load time series is decomposed into several independent IFM components.Taking these independent IFM components as inputs,the short-term load value of distribution network is analyzed by deep confidence network.The fuzzy control method is introduced to take the two common uncertain factors of temperature change and weekends into account,optimize the basic short-term load analysis results calculated by the depth confidence network,and realize the deviation correction.The results show that under the application of the research method,the deviation between the distribution network short-term load level analysis results and the actual results is reduced,especially on Saturday and Sunday,the research goal is achieved,which indicates that the accuracy of distribution network short-term load level analysis is improved.
作者
肖明伟
林其友
杨乐新
汪涵
尹成
XIAO Mingwei;LIN Qiyou;YANG Lexin;WANG Han;YIN Cheng(Wuhu Power Supply Company,State Grid Anhui Electric Power Co.,Ltd.,Wuhu 241027,China)
出处
《微型电脑应用》
2023年第10期168-171,共4页
Microcomputer Applications
关键词
经验模态分解
偏差校正
配电网短期负荷
深度置信网络
水平分析方法
empirical mode decomposition
deviation correction
short term load of distribution network
deep confidence network
horizontal analysis method
