智能电网大数据分析在电力需求预测中的应用  

Application of smart grid big data analytics in electricity demand forecasting

作　　者：朱平飞 王宇坤 于喻 白琳 ZHU Pingfei;WANG Yukun;YU Yu;BAI Lin(Beijing China-Power Information Technology Co.,Ltd.,State Grid Information Telecommunication Group,Beijing 102218,China)

机构地区：[1]国网信息通信产业集团北京中电普华信息技术有限公司,北京102218

出　　处：《集成电路与嵌入式系统》2024年第9期81-86,共6页Integrated Circuits and Embedded Systems

基　　金：国网北京市电力公司科技项目(B20212220016)。

摘　　要：针对智能电网大数据中的异常值,提出了一种基于自适应神经模糊推理系统(ANFIS)的电力需求曲线中的异常值校正方法。该方法针对智能电网中的智能电表进行大数据分析,以检测和校正时序数据中的零值异常。使用实际的电力需求数据验证提出方法的有效性,结果表明,与基于线性插值和人工神经网络的方法相比,ANFIS方法能够以更高的准确率校正异常值,最大相对误差仅为3.76%,相对误差的标准差也更小,为2.26%。实验结果表明,ANFIS方法充分结合了模糊逻辑系统和神经网络的优点,能够很好地处理峰值时段电力负载需求曲线中的异常值,为进一步提高智能电网大数据分析的效果提供了有益借鉴。An adaptive neuro-fuzzy inference system(ANFIS)-based method for correcting outliers in power demand curves is proposed for outliers in smart grid big data.The method performs big data analysis for smart meters in smart grids to detect and correct zero-value anomalies in timing data.The effectiveness of the proposed method is verified using real power demand data,and the results show that the ANFIS method is able to correct the outliers with higher accuracy compared with the linear interpolation and artificial neural network based methods,with a maximum relative error of only 3.76%.In addition,the standard deviation of the relative error is also smaller at 2.26%.The experiment results show that the ANFIS method fully combines the advantages of fuzzy logic system and neural network,effectively dealing with the outliers in the peak hour power load demand curve well.This provides a valuable reference for further improving the effect of smart grid big data analysis.

关 键 词：大数据分析 智能电表 智能电网 ANN ANFIS 

分 类 号：TM391[电气工程—电机]