Online distributed learning in wind power forecasting

Benedikt Sommer, Pierre Pinson*, Jakob W. Messner, David Obst

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Forecasting wind power generation up to a few hours ahead is of the utmost importance for the efficient operation of power systems and for participation in electricity markets. Recent statistical learning approaches exploit spatiotemporal dependence patterns among neighbouring sites, but their requirement of sharing confidential data with third parties may limit their use in practice. This explains the recent interest in distributed, privacy preserving algorithms for high-dimensional statistical learning, e.g. with auto-regressive models. The few approaches that have been proposed are based on batch learning. However, these approaches are potentially computationally expensive and do not allow for the accommodation of nonstationary characteristics of stochastic processes like wind power generation. This paper closes the gap between online and distributed optimisation by presenting two novel approaches that recursively update model parameters while limiting information exchange between wind farm operators and other potential data providers. A simulation study compared the convergence and tracking ability of both approaches. In addition, a case study using a large dataset from 311 wind farms in Denmark confirmed that online distributed approaches generally outperform existing batch approaches while preserving privacy such that agents do not have to actively share their private data.

Original languageEnglish
JournalInternational Journal of Forecasting
Volume37
Issue number1
Pages (from-to)205-223
ISSN0169-2070
DOIs
Publication statusPublished - 1 Jan 2020

Keywords

  • Distributed optimisation
  • Energy forecasting
  • Multivariate time series
  • Online learning
  • Wind energy

Fingerprint Dive into the research topics of 'Online distributed learning in wind power forecasting'. Together they form a unique fingerprint.

Cite this