Picture of neon light reading 'Open'

Discover open research at Strathprints as part of International Open Access Week!

23-29 October 2017 is International Open Access Week. The Strathprints institutional repository is a digital archive of Open Access research outputs, all produced by University of Strathclyde researchers.

Explore recent world leading Open Access research content this Open Access Week from across Strathclyde's many research active faculties: Engineering, Science, Humanities, Arts & Social Sciences and Strathclyde Business School.

Explore all Strathclyde Open Access research outputs...

Very-short-term probabilistic wind power forecasts by sparse vector autoregression

Dowell, Jethro and Pinson, Pierre (2016) Very-short-term probabilistic wind power forecasts by sparse vector autoregression. IEEE Transactions on Smart Grid, 7 (2). pp. 763-770. ISSN 1949-3053

[img]
Preview
Text (Dowell-Pinsen-IEEE-TSG-2015-Very-short-term-probablistic-wind-power)
Dowell_Pinsen_IEEE_TSG_2015_Very_short_term_probablistic_wind_power.pdf - Accepted Author Manuscript

Download (616kB) | Preview

Abstract

A spatio-temporal method for producing very-short-term parametric probabilistic wind power forecasts at a large number of locations is presented. Smart grids containing tens, or hundreds, of wind generators require skilled very-short-term forecasts to operate effectively, and spatial information is highly desirable. In addition, probabilistic forecasts are widely regarded as necessary for optimal power system management as they quantify the uncertainty associated with point forecasts. Here we work within a parametric framework based on the logit-normal distribution and forecast its parameters. The location parameter for multiple wind farms is modelled as a vector-valued spatio-temporal process, and the scale parameter is tracked by modified exponential smoothing. A state-of-the-art technique for fitting sparse vector autoregressive models is employed to model the location parameter and demonstrates numerical advantages over conventional vector autoregressive models. The proposed method is tested on a dataset of 5 minute mean wind power generation at 22 wind farms in Australia. 5-minute-ahead forecasts are produced and evaluated in terms of point and probabilistic forecast skill scores and calibration. Conventional autoregressive and vector autoregressive models serve as benchmarks.