A deep generative model for probabilistic energy forecasting in power systems: normalizing flows

• Published in: Applied energy Vol. 305; p. 117871
• Main Authors: Dumas, Jonathan, Wehenkel, Antoine, Lanaspeze, Damien, Cornélusse, Bertrand, Sutera, Antonio
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2022
• Subjects: case studies; decision making; Deep learning; electricity; energy; Energy forecasting; Generative adversarial networks; Normalizing flows; solar energy; Time series; uncertainty; Variational autoencoders; wind; Deep learning; Variational autoencoders; Generative adversarial networks; Normalizing flows; Energy forecasting; Time series
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2021.117871

Greater direct electrification of end-use sectors with a higher share of renewables is one of the pillars to power a carbon-neutral society by 2050. However, in contrast to conventional power plants, renewable energy is subject to uncertainty raising challenges for their interaction with power systems. Scenario-based probabilistic forecasting models have become a vital tool to equip decision-makers. This paper presents to the power systems forecasting practitioners a recent deep learning technique, the normalizing flows, to produce accurate scenario-based probabilistic forecasts that are crucial to face the new challenges in power systems applications. The strength of this technique is to directly learn the stochastic multivariate distribution of the underlying process by maximizing the likelihood. Through comprehensive empirical evaluations using the open data of the Global Energy Forecasting Competition 2014, we demonstrate that this methodology is competitive with other state-of-the-art deep learning generative models: generative adversarial networks and variational autoencoders. The models producing weather-based wind, solar power, and load scenarios are properly compared in terms of forecast value by considering the case study of an energy retailer and quality using several complementary metrics. The numerical experiments are simple and easily reproducible. Thus, we hope it will encourage other forecasting practitioners to test and use normalizing flows in power system applications such as bidding on electricity markets, scheduling power systems with high renewable energy sources penetration, energy management of virtual power plan or microgrids, and unit commitment. •Probabilistic forecasting with a recent deep learning technique: normalizing flows.•Generative models to compute weather-based PV, wind power, and load scenarios.•Extensive evaluation both in terms of quality and value.•Comparison with generative adversarial networks and variational autoencoders.•Empirical evaluations using the Global Energy Forecasting Competition 2014 data.