Deep Distributional Time Series Models and the Probabilistic Forecasting of Intraday Electricity Prices
This work addresses the complex task of forecasting intraday electricity prices, which is crucial for energy market participants, but it is incremental as it builds on existing RNN and copula methods.
The authors tackled the problem of probabilistic forecasting for intraday electricity prices by proposing two deep time series models based on echo state networks, with the copula model dominating and showing significant improvements in upper tail forecast accuracy when incorporating demand forecasts.
Recurrent neural networks (RNNs) with rich feature vectors of past values can provide accurate point forecasts for series that exhibit complex serial dependence. We propose two approaches to constructing deep time series probabilistic models based on a variant of RNN called an echo state network (ESN). The first is where the output layer of the ESN has stochastic disturbances and a shrinkage prior for additional regularization. The second approach employs the implicit copula of an ESN with Gaussian disturbances, which is a deep copula process on the feature space. Combining this copula with a non-parametrically estimated marginal distribution produces a deep distributional time series model. The resulting probabilistic forecasts are deep functions of the feature vector and also marginally calibrated. In both approaches, Bayesian Markov chain Monte Carlo methods are used to estimate the models and compute forecasts. The proposed models are suitable for the complex task of forecasting intraday electricity prices. Using data from the Australian National Electricity Market, we show that our deep time series models provide accurate short term probabilistic price forecasts, with the copula model dominating. Moreover, the models provide a flexible framework for incorporating probabilistic forecasts of electricity demand as additional features, which increases upper tail forecast accuracy from the copula model significantly.