Analytical iterative multi-step interval forecasts of wind generation based on TLGP

Juan Yan, Kang Li, Erwei Bai, Xiaodong Zhao, Yusheng Xue, Aoife M. Foley

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)
277 Downloads (Pure)


Probabilistic wind power forecasting has become an important tool for optimal economic dispatch and unit commitment of modern power systems with significant renewable energy penetrations. Ensemble forecasting based on Monte Carlo simulation is commonly used by many grid operators, but other probabilistic approaches, such as multi-step iterative wind power forecasting have not yet been fully explored. The associated uncertainty analysis is an important yet challenging issue in this area. This paper proposes to use an analytic interval forecasting framework to estimate the forecasting uncertainty of a wind farm in Ireland based on the Temporally Local Gaussian Process (TLGP) model and evaluates the probabilistic forecasting metrics of reliability and sharpness. The key findings confirm that TLGP not only has better forecasting accuracy but is also less sensitive to uncertainty propagation than Gaussian Process (GP). This work provides an effective analytical framework for iterative multi-step interval forecasting.
Original languageEnglish
Pages (from-to)625-636
Number of pages12
JournalIEEE Transactions on Sustainable Energy
Issue number2
Early online date29 May 2018
Publication statusPublished - 01 Apr 2019


  • Forecasting
  • Gaussian process
  • Gaussian processes
  • Predictive models
  • Probabilistic logic
  • Uncertainty
  • Wind forecasting
  • Wind power generation
  • probabilistic forecasting
  • uncertainty propogation
  • wind energy

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment


Dive into the research topics of 'Analytical iterative multi-step interval forecasts of wind generation based on TLGP'. Together they form a unique fingerprint.

Cite this