摘要
随着智能电网和能源互联网的发展,实时传输的数据量显著增加。由于缺乏承载高速和实时数据的通信网络,数据丢失和数据质量下降。针对这一问题,本文根据电量数据由人的动作和感受产生,具有强烈的时空相关性,构造行为时间和列为用户的低秩电量数据矩阵,然后根据矩阵分解思想,将低秩矩阵分解成2个矩阵乘积,利用已知矩阵数据来近似原始低秩矩阵,以恢复丢失的数据。分析真实电量数据的低秩性,并进行基于矩阵分解恢复方法的实验,实验结果表明该方法具有较高效率和准确率。
The development of smart grid and energy internet has led to a significant increase in the amount of data transmitted in real time. Data is lost and data quality declines due to the lack of communication networks carrying high-speed and real-time data. For this problem, according to the strong spatial and temporal correlation of electricity data which is generated by human's actions and feelings, we build a low-rank electricity data matrix where the row is time and the column is user. Inspired by matrix factorization, we divide the low-rank electricity data matrix into the multiply of two small matrices and use the known data to approximate the low-rank electricity data matrix and recover the missed electrical data. Based on the real electricity data, we analyze the low-rankness of the electricity data matrix and perform the Matrix Factorization-based recover method on the real data. The experimental results verify the efficiency and accuracy of the proposed scheme.
作者
何燕文
党倩
尚闻博
罗发政
HE Yanwen;DANG Qian;SHANG Wenbo;LUO Fazheng(State Grid Gansu Electric Power Company,Lanzhou 730050,China;Information & Communication Company,State Grid Gansu Electric Power Company,Lanzhou 730050,China)
出处
《电力信息与通信技术》
2018年第10期81-85,共5页
Electric Power Information and Communication Technology
关键词
电量数据恢复
矩阵分解
低秩矩阵
electrical data recovery
matrix factorization
sparse matrix