Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study

TL;DR

This study compares various RNN architectures with different gated cells, including new variants with dilation and attention, for forecasting complex time series with multiple seasonal patterns, demonstrating superior performance in electrical load prediction.

Contribution

Introduces and evaluates new gated RNN cells with dilation and attention mechanisms for improved multi-seasonality time series forecasting.

Findings

New gated cells outperform traditional ones in accuracy.

Hierarchical dilated RNNs effectively model multi-scale dependencies.

Proposed models provide accurate point forecasts and predictive intervals.

Abstract

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.