Multi-source transfer learning guided ensemble LSTM for building multi-load forecasting

作者：

Highlights：

• Propose a multi-source transfer learning-guided ensemble LSTM method.

• Develop a two-stage matching method of source domain building.

• Give a LSTM modeling strategy with transfer learning and fine-tune technology.

• Give a model ensemble strategy based on similarity degree.

摘要

•Propose a multi-source transfer learning-guided ensemble LSTM method.•Develop a two-stage matching method of source domain building.•Give a LSTM modeling strategy with transfer learning and fine-tune technology.•Give a model ensemble strategy based on similarity degree.

论文关键词：Building load forecasting,Transfer learning,Multi-source,LSTM

论文评审过程：Received 14 September 2021, Revised 23 March 2022, Accepted 4 April 2022, Available online 20 April 2022, Version of Record 27 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117194