Feature engineering and forecasting via derivative-free optimization and ensemble of sequence-to-sequence networks with applications in renewable energy

Mohammad Pirhooshyaran, Katya Scheinberg and Lawrence V. Snyder

Energy, 2020, vol. 196, issue C

Abstract: This study introduces a framework for the forecasting and feature engineering of multivariate processes along with their renewable energy applications. Derivative-free optimization is integrated with an ensemble of sequence-to-sequence networks to design a new resampling technique called additive resampling to exploit the repetitive behavior of time series, particularly the characteristics of renewable energy. The performance of the proposed framework is explored on three renewable energy sources—wind, solar and ocean wave—on which several short-to long-term forecasts are conducted to show the superiority of the proposed method compared to numerous machine learning techniques. The findings indicate that the introduced method performs more accurately when the forecasting horizon becomes longer. In addition, the framework for automated feature selection is modified. The model represents a clear interpretation of the selected features. Furthermore, we investigate the effects of different environmental and marine factors on the wind speed and ocean output power, respectively, and report the selected features. Finally, the online forecasting setting is explored and used to illustrate that the model outperforms alternatives through different measurement errors.

Keywords: Ensemble sequence-to-sequence networks; Renewable energy; Derivative-free optimization; Automated feature selection; Online forecasting (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544220302437
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:196:y:2020:i:c:s0360544220302437

DOI: 10.1016/j.energy.2020.117136

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().