Yuting Bai

TL;DR: An attention-based encoder-decoder network with Bayesian optimization is proposed to do the accurate short-term power load forecasting, providing an effective approach for migrating time-serial power load prediction by deep-learning technology.

TL;DR: A novel planar flow-based variational auto-encoder prediction model (PFVAE) is proposed, which uses the long- and short-term memory network (LSTM) as the auto- Encoder and designs the variational Auto-Encoder (VAE), as a time series data predictor to overcome the noise effects.

TL;DR: A Reversible Automatic Selection Normalization (RASN) network is proposed, integrating the normalization and renormalization layer to evaluate and select thenormalization module of the prediction model, showing good prediction ability and adaptability for the greenhouse in the Smart Agriculture System.

TL;DR: A hybrid deep learning predictor is proposed, in which an empirical mode decomposition (EMD) method is used to decompose the climate data into fixed component groups with different frequency characteristics, then a gated recurrent unit (GRU) network is trained for each group as the sub-predictor, and finally the results from the GRU are added to obtain the prediction result.

TL;DR: A data self-screening layer with a maximal information distance coefficient (MIDC) is designed to filter input data with high correlation and low redundancy and a variational Bayesian gated recurrent unit is used to improve the anti-noise ability and robustness of the model.