Missing data in wind farm time series : properties and effect on forecasts
Tawn, Rosemary and Browell, Jethro and Dinwoodie, Iain (2020) Missing data in wind farm time series : properties and effect on forecasts. Electric Power Systems Research, 189. 106640. ISSN 0378-7796 (https://doi.org/10.1016/j.epsr.2020.106640)
Preview |
Text.
Filename: Tawn_etal_EPSR_2020_Missing_data_in_wind_farm_time_series.pdf
Accepted Author Manuscript License: Download (250kB)| Preview |
Abstract
Missing or corrupt data is common in real-world datasets; this affects the estimation and operation of analytical models where completeness is assumed or required. Statistical wind power forecasts utilise recent turbine data as model inputs, and must therefore be robust to missing data. We find that wind power data is ‘missing not at random’, with missing patterns also related to the forecast output. Approaches for dealing with this missing data in training and operation are proposed and evaluated through a case study, leading to a suggested forecasting methodology in the presence of missing data. In the training set, missing data was found to have significant negative impact on performance if simply omitted but this can be almost completely mitigated using multiple imputation. Greater increase in forecast errors is seen when input data are missing operationally, and retraining forecast models using the remaining inputs is found to be preferable to imputation.
ORCID iDs
Tawn, Rosemary, Browell, Jethro ORCID: https://orcid.org/0000-0002-5960-666X and Dinwoodie, Iain;-
-
Item type: Article ID code: 72087 Dates: DateEvent31 December 2020Published11 August 2020Published Online11 February 2020AcceptedSubjects: Technology > Electrical engineering. Electronics Nuclear engineering Department: Faculty of Engineering > Electronic and Electrical Engineering Depositing user: Pure Administrator Date deposited: 17 Apr 2020 12:49 Last modified: 03 Dec 2024 01:20 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/72087