B1772
Title: Advanced methods for modelling and forecasting electricity prices
Authors: Gernot Mueller - University of Augsburg (Germany) [presenting]
Daniel Nickelsen - University of Augsburg (Germany)
Sebastian Uhl - University of Augsburg (Germany)
Abstract: In the past years, the increasing infeed from renewable energies became responsible for a large part of the variation in electricity prices at the European Energy Exchange (EEX). For instance, models based on Levy processes have been used successfully to describe the behaviour of the day-ahead market. At the same time, the intraday market is highly dynamic with outstanding liquidity and steadily increasing traded volumes, and, hence, a challenging and important topic for risk management. statistical approaches are considered for modelling and forecasting electricity prices. The target of the analyses is price indices used for the intraday market at the EEX, e.g. ID3 and IDFull, which represent weighted average prices over different time periods before delivery. In particular, a Bayesian approach is set up for forecasting the price spread between the intraday and the day-ahead market using predictive distributions. This way forecasts are produced for the price trends on the intraday market and, in addition, the quality of these forecasts is assessed using predictive probabilities. Finally, it is also investigated whether the forecasting quality can be further improved using artificial intelligence.
