摘要
随着智能电表的广泛应用,电网公司积累了大量原始用电数据,然而复杂工作环境下用电信息采集设备仍存在数据丢失的现象。在充分考虑高斯噪声影响的情况下,对存在缺失的原始用电数据进行填补。对独立用户数据序列重排得到原始用电数据矩阵,将其中的理想用电数据矩阵进行非负矩阵分解替代;分别选择F范数和核范数对高斯噪声和具有低秩特性的理想用电数据进行正则化约束以构建优化模型;最后,基于块坐标最小算法框架使用EM算法和直接法交替更新非负矩阵分解得到的矩阵因子,从而有效实现数据的准确插补。仿真分析和实验结果验证了算法的有效性和准确性。
With the widespread deployment of smart meters,power grids have accumulated vast amounts of raw electricity consumption data.However,data loss remains a challenge due to the complex operational environments of data acquisition equipment.This study addresses the problem of incomplete electricity consumption data by accounting for the influence of Gaussian noise and proposing a robust completion method.First,a electricity consumption data matrix is constructed by reorganizing the sequences of individual users,and the ideal electricity data matrix is approximated using nonnegative matrix factorization(NMF).Second,both the Frobenius norm and the nuclear norm are employed to regularize the Gaussian noise and promote low-rank characteristics of the ideal matrix,thereby formulating an optimization model.Finally,within a block coordinate descent framework,the EM algorithm and a direct updating method are applied alternately to update the matrix factors derived from NMF,enabling accurate and complete data reconstruction.Simulation and experimental results validate the proposed algorithm’s effectiveness and accuracy.
作者
钟尧
刘清蝉
李昕泓
林聪
李腾斌
杨超
付志红
ZHONG Yao;LIU Qingchan;LI Xinhong;LIN Cong;LI Tengbin;YANG Chao;FU Zhihong(Measurement Center of Yunnan Power Grid Co.,Kunming 650000,P.R.China;School of Electrical Engineering,Chongqing University,Chongqing 400044,P.R.China)
出处
《重庆大学学报》
北大核心
2025年第9期1-11,共11页
Journal of Chongqing University
基金
云南电网科技资助项目(YNKJXM20210147)。
关键词
用电数据
非负矩阵分解
范数
块坐标下降法
矩阵完备
electricity consumption data
nonnegative matrix factorization
norm
block coordinate descent
matrix completion
作者简介
钟尧(1983—),男,高级工程师,主要从事电能计量及智能运维研究,(E-mail)93336425@qq.com。;通信作者:李昕泓,女,(E-mail)1347240996@qq.com。
