Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond

By Tao Hong, Pierre Pinson, Shu Fan, H. Zareipour, A. Troccoli, Rob J Hyndman. 2016

969 citations recorded by the source corpus.

The energy industry has been going through a significant modernization process over the last decade. Its infrastructure is being upgraded rapidly. The supply, demand and prices are becoming more volatile and less predictable than ever before. Even its business model is being challenged fundamentally. In this competitive and dynamic environment, many decision-making processes rely on probabilistic forecasts to quantify the uncertain future. Although most of the papers in the energy forecasting literature focus on point or single-valued forecasts, the research interest in probabilistic energy forecasting research has taken off rapidly in recent years. In this paper, we summarize the recent research progress on probabilistic energy forecasting. A major portion of the paper is devoted to introducing the Global Energy Forecasting Competition 2014 (GEFCom2014), a probabilistic energy forecasting competition with four tracks on load, price, wind and solar forecasting, which attracted 581 participants from 61 countries. We conclude the paper with 12 predictions for the next decade of energy forecasting.

Subfields: Economics and Econometrics, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Electrical and Electronic Engineering

Citations in the corpus

A Multi-Horizon Quantile Recurrent Forecaster (2017, methodology): “Next, we apply our forecasting framework to the Global Energy Forecasting Com-Figure petition 2014 (GEFCom2014, Hong et al, 2016) to demonstrate that the model is ﬂexible, easy to use and powerful: our result would have won the 1st place in this competition, without much tuning.”
Gaining Insight Into Solar Photovoltaic Power Generation Forecasting Utilizing Explainable Artificial Intelligence Tools (2020, methodology): “A popular open-source benchmark dataset from the Global Energy Forecasting Competition (GEFCOM) held in 2014 [38] is used for this work.”
Review of low voltage load forecasting: Methods, applications, and recommendations (2021, background): “In particular, GEFCom2014 considered probabilistic load forecasts at two levels with the loads mostly at 4kV and 12kV [101].”
A new high-dimensional time series approach for wind speed, wind direction and air pressure forecasting (2017, background): “Taylor et al. (2009), Hong et al. (2016) and Iversen et al. (2016) emphasize the benefit of probabilistic forecasts in the context of wind speed and wind power predictions.”
Forecasting wind power – Modeling periodic and non-linear effects under conditional heteroscedasticity (2016, positive): “As pointed out by, e.g., Pinson et al. (2013), Alessandrini et al. (2013), and Hong et al. (2016), the importance of probabilistic wind power forecasting is increasing, especially for longer forecasting horizons.”
Recent advances in electricity price forecasting: A review of probabilistic forecasting (2016, methodology): “[3], however, during the competition the information set was being extended on a weekly basis to prevent ‘peeking’ into the future.”
Variance Stabilizing Transformations for Electricity Spot Price Forecasting (2018, methodology): “However, robust techniques are not popular in the EPF literature, while the latter generally do not outperform linear models in short-term EPF [1], [16].”
Deep Learning for Time Series Forecasting: The Electric Load Case (2019, methodology): “The other two use cases are based on the GEFCom2014dataset [35], which was made available for an online forecasting competition that lasted between August 2015 and December 2015.”
Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges (2018, background): “and high-rank forecasting methods in this competition are summarized in [57].”
Multi-Horizon Time Series Forecasting with Temporal Attention Learning (2019, methodology): “We apply our approach to multi-horizon forecasting problems on a large-scale public forecasting dataset - the GEFCom2014 Electricity Price Forecasting dataset, and a huge real-world dataset with daily sales of 50,000 products on JD.com - the JD50K sales dataset.”
Forecasting: theory and practice (2020, methodology): “A winning team of the Global Energy Forecasting Competition 2014 (GEFCom2014) also incorporated a model-based approach for anomaly detection and data cleansing (Xie and Hong, 2016).”