Complexity and Persistence of Price Time Series of the European Electricity Spot Market

Han, Chengyuan; Hilger, Hannes; Mix, Eva; Böttcher, Philipp; Reyers, Mark; Beck, Christian; Witthaut, Dirk; Gorjão, Leonardo Rydin

doi:10.1103/prxenergy.1.013002

Cited by 14 publications

(13 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of electricity is traded on the auctionbased day-ahead market, while the intraday market is primarily used to make short-term adjustments to the previously submitted bids (Han et al, 2022). The intraday contracts are negotiated between the producers and the consumers on different time horizons and for different periods.…”

Section: Data Descriptionmentioning

confidence: 99%

“…For instance, a scheduled ramp up of electricity supply results in an undersupply in the first 15 minutes and an oversupply in the last 15 minutes of the respective hour, which leads to higher prices in the first 15 minutes and lower prices in the last 15 minutes, respectively. Thus, the hour-wise constant day-ahead contracts lead to hourly patterns in the 15 min intraday prices (Kiesel and Paraschiv, 2017;Han et al, 2022).…”

Section: Hourly Price Difference Vectorsmentioning

confidence: 99%

“…However, the proposed model considers the difference between the two market prices, which alleviates the impact of some external factors and amplifies the impact of others. In particular, the impact of the forecasted total electricity demand and the forecasted total renewable electricity supply is already considered in the day-ahead market and has little influence on the price differences (Kiesel and Paraschiv, 2017;Spodniak et al, 2021;Han et al, 2022). The intraday markets are used to adjust the previously submitted bids on the day-ahead market, which are based on forecasts.…”

Section: External Factorsmentioning

confidence: 99%

“…The intraday markets are used to adjust the previously submitted bids on the day-ahead market, which are based on forecasts. Thus, the differences are mostly impacted by the forecasting errors for demand and renewables (Kiesel and Paraschiv, 2017;Han et al, 2022). The renewable forecast errors are computed as the difference between the realization and the forecast:…”

Section: External Factorsmentioning

confidence: 99%

“…Furthermore, the adjustments react to the ramping of supply and demand, which leads to steadily increasing or decreasing prices in the four intraday trading intervals of each day-ahead trading interval (Kiesel and Paraschiv, 2017). Thus, there is a distinct hourly fluctuation of the intraday prices around the day-ahead prices that averages to the day-ahead price (Kiesel and Paraschiv, 2017;Han et al, 2022). This work proposes a modeling approach for intraday electricity prices based on the special relationship between the two electricity markets.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multivariate Probabilistic Forecasting of Intraday Electricity Prices using Normalizing Flows

Cramer¹,

Witthaut²,

Mitsos³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Electricity is traded on various markets with different time horizons and regulations. Short-term trading becomes increasingly important due to higher penetration of renewables. In Germany, the intraday electricity price typically fluctuates around the day-ahead price of the EPEX spot markets in a distinct hourly pattern. This work proposes a probabilistic modeling approach that models the intraday price difference to the day-ahead contracts. The model captures the emerging hourly pattern by considering the four 15 min intervals in each day-ahead price interval as a four-dimensional joint distribution. The resulting nontrivial, multivariate price difference distribution is learned using a normalizing flow, i.e., a deep generative model that combines conditional multivariate density estimation and probabilistic regression. The normalizing flow is compared to a selection of historical data, a Gaussian copula, and a Gaussian regression model. Among the different models, the normalizing flow identifies the trends most accurately and has the narrowest prediction intervals. Notably, the normalizing flow is the only approach that identifies rare price peaks. Finally, this work discusses the influence of different external impact factors and finds that, individually, most of these factors have negligible impact. Only the immediate history of the price difference realization and the combination of all input factors lead to notable improvements in the forecasts.

show abstract

Section: Data Descriptionmentioning

confidence: 99%

Section: Hourly Price Difference Vectorsmentioning

confidence: 99%