Hierarchical electricity time series prediction with cluster analysis and sparse penalty

作者：

Highlights：

• A novel hierarchical forecasting approach based on multiple alternative clustering.

• A sparse penalty method of group Lasso is introduced to automatically select the ideal clusters.

• Experiments on various real-life electricity and solar power datasets.

摘要

•A novel hierarchical forecasting approach based on multiple alternative clustering.•A sparse penalty method of group Lasso is introduced to automatically select the ideal clusters.•Experiments on various real-life electricity and solar power datasets.

论文关键词：Hierarchical time series forecasting,Data mining,Machine learning

论文评审过程：Received 9 April 2021, Revised 17 December 2021, Accepted 24 January 2022, Available online 26 January 2022, Version of Record 6 February 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108555