Forecasting Prices in Power Markets

A special issue of Forecasting (ISSN 2571-9394). This special issue belongs to the section "Power and Energy Forecasting".

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 7079

Special Issue Editors

House of Energy Markets and Finance, University of Duisburg-Essen, Universitätsstraße 2, 45141 Essen, Germany
Interests: energy analytics; electricity price and load forecasting; energy markets; renewable energy; forecasting in water and environmental sciences; high-dimensional time series; seasonal time series; probabilistic forecasting; evaluation; risk and portfolio management
Special Issues, Collections and Topics in MDPI journals
Department of Applied Mathematics, University of the Basque Country, UPV/EHU. Torres Quevedo Ingeniaria Plaza, 1, 48013 Bilbo, Spain
Interests: electricity markets’ data analysis; electricity price forecasting; energy markets; renewable energy; high-dimensional time series; probabilistic forecasting; evaluation

Special Issue Information

Dear Colleagues,

The increasing liberalization and interconnection of power markets, and the growing importance of renewable energies, storage and demand response lead to complex electricity price formation on power markets. To reduce carbon emissions and the impact of climate change, accurate forecasts are required for efficient decision making. This concerns all forecasting horizons, ranging from short-term horizons with substantial impact from meteorological conditions, whereas long-term forecasts are mainly influenced by economical, regulatory and technological risk. Power has unique characteristics (especially concerning required system balance and storage opportunities) not found in other commodities. Usually, electricity price data may exhibit specific characteristics, like

(i) (time-varying) autoregressive effects and (in)stationarity

(ii) calendar effects (daily, weekly and annual seasonality, holiday effects, clockchange)

(iii) (time-varying) volatility and higher moment effects

(iv) (positive and negative) price spikes

(v) price clustering.

Some of these effects may be explained by external input data available at prediction time. However, electricity price forecasting remains a challenging task. We welcome scientific contributions on forecasting power/electricity prices that give insights into a better understanding of power price dynamics for all kinds of forecasting horizons and power markets (e.g., derivative markets, spot markets, day-ahead markets, intraday and balancing markets). We particularly welcome contributions in the area of probabilistic forecasting using all kinds of methods. This may be suitable for statistical time series prediction methods or machine learning methods, like gradient boosting machines (GBM) or artificial neural networks (ANN). In this Special Issue, we invite submissions exploring cutting-edge research and recent advances that address the above and related challenges.

Prof. Dr. Florian Ziel
Prof. Dr. Peru Muniain
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Forecasting is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • power price formation
  • electricity price forecasting
  • predictive analytics
  • probabilistic forecasting
  • machine learning
  • neural networks
  • statistical models

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 500 KiB  
Article
Event-Based Evaluation of Electricity Price Ensemble Forecasts
by Arne Vogler and Florian Ziel
Forecasting 2022, 4(1), 51-71; https://0-doi-org.brum.beds.ac.uk/10.3390/forecast4010004 - 29 Dec 2021
Cited by 2 | Viewed by 2068
Abstract
The present paper considers the problem of choosing among a collection of competing electricity price forecasting models to address a stochastic decision-making problem. We propose an event-based evaluation framework applicable to any optimization problem, where uncertainty is captured through ensembles. The task of [...] Read more.
The present paper considers the problem of choosing among a collection of competing electricity price forecasting models to address a stochastic decision-making problem. We propose an event-based evaluation framework applicable to any optimization problem, where uncertainty is captured through ensembles. The task of forecast evaluation is simplified from assessing a multivariate distribution over prices to assessing a univariate distribution over a binary outcome directly linked to the underlying decision-making problem. The applicability of our framework is demonstrated for two exemplary profit-maximization problems of a risk-neutral energy trader, (i) the optimal operation of a pumped-hydro storage plant and (ii) the optimal trading of subsidized renewable energy in Germany. We compare and contrast the approach with the full probabilistic and profit–loss-based evaluation frameworks. It is concluded that the event-based evaluation framework more reliably identifies economically equivalent forecasting models, and in addition, the results suggest that an event-based evaluation specifically tailored to the rare event is crucial for decision-making problems linked to rare events. Full article
(This article belongs to the Special Issue Forecasting Prices in Power Markets)
Show Figures

Figure 1

37 pages, 2572 KiB  
Article
Probabilistic Day-Ahead Wholesale Price Forecast: A Case Study in Great Britain
by Stephen Haben, Julien Caudron and Jake Verma
Forecasting 2021, 3(3), 596-632; https://0-doi-org.brum.beds.ac.uk/10.3390/forecast3030038 - 28 Aug 2021
Cited by 6 | Viewed by 4124
Abstract
The energy sector is moving towards a low-carbon, decentralised, and smarter network. The increased uptake of distributed renewable energy and cheaper storage devices provide opportunities for new local energy markets. These local energy markets will require probabilistic price forecasting models to better describe [...] Read more.
The energy sector is moving towards a low-carbon, decentralised, and smarter network. The increased uptake of distributed renewable energy and cheaper storage devices provide opportunities for new local energy markets. These local energy markets will require probabilistic price forecasting models to better describe the future price uncertainty. This article considers the application of probabilistic electricity price forecasting models to the wholesale market of Great Britain (GB) and compares them to better understand their capabilities and limits. One of the models that this paper considers is a recent novel X-model that predicts the full supply and demand curves from the bid-stack. The advantage of this model is that it better captures price spikes in the data. In this paper, we provide an adjustment to the model to handle data from GB. In addition to this, we then consider and compare two time-series approaches and a simple benchmark. We compare both point forecasts and probabilistic forecasts on real wholesale price data from GB and consider both point and probabilistic measures. Full article
(This article belongs to the Special Issue Forecasting Prices in Power Markets)
Show Figures

Figure 1

Back to TopTop