Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study
It addresses forecasting challenges for time series with complex patterns, such as electrical load, but is incremental as it builds on existing RNN methods.
This paper tackled forecasting time series with multiple seasonality by comparing recurrent neural networks with various gated cells, including new ones with dilation and attention, and found that these new cells performed best in an electrical load forecasting study across 35 European countries.
This paper compares recurrent neural networks (RNNs) with different types of gated cells for forecasting time series with multiple seasonality. The cells we compare include classical long short term memory (LSTM), gated recurrent unit (GRU), modified LSTM with dilation, and two new cells we proposed recently, which are equipped with dilation and attention mechanisms. To model the temporal dependencies of different scales, our RNN architecture has multiple dilated recurrent layers stacked with hierarchical dilations. The proposed RNN produces both point forecasts and predictive intervals (PIs) for them. An empirical study concerning short-term electrical load forecasting for 35 European countries confirmed that the new gated cells with dilation and attention performed best.