A1 Journal article (refereed), original research

Assessing the performance of deep learning models for multivariate probabilistic energy forecasting


Open Access hybrid publication


Publication Details

Authors: Mashlakov Aleksei, Kuronen Toni, Lensu Lasse, Kaarna Arto, Honkapuro Samuli

Publisher: Elsevier

Publication year: 2021

Language: English

Related journal or series: Applied Energy

Volume number: 285

ISSN: 0306-2619

JUFO level of this publication: 3

Digital Object Identifier (DOI): http://dx.doi.org/10.1016/j.apenergy.2020.116405

Permanent website address: https://www.sciencedirect.com/science/article/pii/S0306261920317748

Social media address: https://www.researchgate.net/publication/348558470_Assessing_the_performance_of_deep_learning_models_for_multivariate_probabilistic_energy_forecasting

Open Access: Open Access hybrid publication

Location of the parallel saved publication: http://urn.fi/URN:NBN:fi-fe202101222501

Research data location: https://github.com/aleksei-mashlakov/multivariate-deep-learning


Abstract

Deep learning models have the potential to advance the short-term
decision-making of electricity market participants and system operators
by capturing the complex dependences and uncertainties of power system
operation. Currently, however, the adoption of global deep learning
models for multivariate energy forecasting in power systems is far
behind the developments in the deep learning research field. In this
context, the objectives of this study are to review recent developments
in the field of probabilistic, multivariate, and multihorizon time
series forecasting and empirically evaluate the performance of novel
global deep learning models for forecasting wind and solar generation,
electricity load, and wholesale electricity price for intraday and
day-ahead time horizons. Two forecast types, deterministic and
probabilistic forecasts, are studied. The evaluation data consist of
real-world datasets with hourly resolution at the levels of an
individual customer and regional and national electricity market bidding
zones. The model evaluation criteria include achievable levels of
forecasting accuracy and uncertainty risks, hyperparameter sensitivity,
the effect of exogenous variables and fieldwise dataset split, and
run-time efficiency factors, such as memory utilization, simulation
time, electricity consumption, and convergence rate. We conclude that
the performance of the global models is more beneficial for intraday
forecasts of heterogeneous datasets with nonuniform patterns of time
series, but can be affected by the hyperparameter sensitivity and
hardware limitations with the growth of dataset dimensionality. The
results can serve as a reference point for the quantitative evaluation
of deep learning models for probabilistic multivariate energy
forecasting in power systems.


Last updated on 2021-10-02 at 07:46