An estimating combination method for interval forecasting of electrical load time series

作者：

Highlights：

• Propose an estimating combination method for electrical load interval forecasting.

• Conduct feature selection to identify characteristics of original time series.

• Combine Gaussian distribution with deep neural network.

• Build an index table to include all information of prediction intervals.

摘要

•Propose an estimating combination method for electrical load interval forecasting.•Conduct feature selection to identify characteristics of original time series.•Combine Gaussian distribution with deep neural network.•Build an index table to include all information of prediction intervals.

论文关键词：Interval forecasting,Machine learning method,Distribution estimation,Feature selection,Electrical load time series

论文评审过程：Received 17 July 2019, Revised 28 April 2020, Accepted 28 April 2020, Available online 7 May 2020, Version of Record 20 May 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113498