Ensemble incremental learning Random Vector Functional Link network for short-term electric load forecasting
作者：
Highlights：
• An ensemble incremental learning method is proposed for electric load forecasting.
• DWT and EMD are sequentially combined to decompose load time series signal.
• Each sub-signal is modeled by an incremental learning RVFL network.
• Temperature data is used to improve the performance of electric load forecasting.
• The proposed method has advantages based on both accuracy and efficiency.
摘要
•An ensemble incremental learning method is proposed for electric load forecasting.•DWT and EMD are sequentially combined to decompose load time series signal.•Each sub-signal is modeled by an incremental learning RVFL network.•Temperature data is used to improve the performance of electric load forecasting.•The proposed method has advantages based on both accuracy and efficiency.
论文关键词：Empirical Mode Decomposition,Discrete wavelet transform,Random Vector Functional Link network,Incremental learning,Time series forecasting,Electric load forecasting,Neural networks,Random forests
论文评审过程：Received 1 August 2017, Revised 15 January 2018, Accepted 18 January 2018, Available online 1 February 2018, Version of Record 20 February 2018.
论文官网地址：https://doi.org/10.1016/j.knosys.2018.01.015
