Towards missing electric power data imputation for energy management systems

作者：

Highlights：

• Statistical and machine learning methods for imputing missing electric power data are studied.

• Multiple missing feature values of each electric power data are considered.

• The performance of different methods over the summer and non-summer season data is compared.

• The imputation performances during the peak, off-peak, and semi-peak times are examined.

摘要

•Statistical and machine learning methods for imputing missing electric power data are studied.•Multiple missing feature values of each electric power data are considered.•The performance of different methods over the summer and non-summer season data is compared.•The imputation performances during the peak, off-peak, and semi-peak times are examined.

论文关键词：Data mining,Electric power data,Energy management system,Missing value imputation,Machine learning

论文评审过程：Received 11 August 2020, Revised 24 December 2020, Accepted 13 February 2021, Available online 20 February 2021, Version of Record 7 March 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114743