A novel trilinear deep residual network with self-adaptive Dropout method for short-term load forecasting

作者：

Highlights：

• A novel deep residual network with self-adaptive Dropout method is proposed.

• A trilinear deep residual network solves vanishing gradient and exploding gradient.

• The self-adaptive Dropout method sets the neuron drop ratio automatically.

• The neural network ensemble method enhances the forecasting accuracy.

• The performance of the proposed model is superior to other comparative models.

摘要

•A novel deep residual network with self-adaptive Dropout method is proposed.•A trilinear deep residual network solves vanishing gradient and exploding gradient.•The self-adaptive Dropout method sets the neuron drop ratio automatically.•The neural network ensemble method enhances the forecasting accuracy.•The performance of the proposed model is superior to other comparative models.

论文关键词：Load forecasting,Deep residual network,Dropout,Ensemble learning,Deep learning

论文评审过程：Received 17 December 2020, Revised 9 March 2021, Accepted 21 May 2021, Available online 27 May 2021, Version of Record 2 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115272