Deep Distributional Time Series Models and the Probabilistic Forecasting of Intraday Electricity Prices

10/05/2020
by   Nadja Klein, et al.
0

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 deep time series models are suitable for the complex task of forecasting intraday electricity prices. Using data from the Australian National Electricity Market, we show that our models provide accurate probabilistic price forecasts. Moreover, the models provide a flexible framework for incorporating probabilistic forecasts of electricity demand as additional features. We demonstrate that doing so in the deep distributional time series model in particular, increases price forecast accuracy substantially.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2022

From point forecasts to multivariate probabilistic forecasts: The Schaake shuffle for day-ahead electricity price forecasting

Modeling price risks is crucial for economic decision making in energy m...
research
01/31/2021

Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting

Probabilistic time series forecasting involves estimating the distributi...
research
12/06/2018

Using published bid/ask curves to error dress spot electricity price forecasts

Accurate forecasts of electricity spot prices are essential to the daily...
research
06/25/2016

Probabilistic Forecasting and Simulation of Electricity Markets via Online Dictionary Learning

The problem of probabilistic forecasting and online simulation of real-t...
research
06/14/2019

Machine Learning on EPEX Order Books: Insights and Forecasts

This paper employs machine learning algorithms to forecast German electr...
research
08/05/2017

Construction and Visualization of Optimal Confidence Sets for Frequentist Distributional Forecasts

The focus of this paper is on the quantification of sampling variation i...
research
02/21/2020

A copula-based time series model for global horizontal irradiation

The increasing importance of solar power for electricity generation lead...

Please sign up or login with your details

Forgot password? Click here to reset