Version 1
: Received: 17 May 2024 / Approved: 17 May 2024 / Online: 21 May 2024 (10:34:00 CEST)
How to cite:
Shoukat, G.; Malekjafarian, A.; Pakrashi, V. A Comparative Study for Using Deep LSTMs and ARIMA for Imputing Missing Data for Wind Data in the Irish Sea. Preprints2024, 2024051179. https://doi.org/10.20944/preprints202405.1179.v1
Shoukat, G.; Malekjafarian, A.; Pakrashi, V. A Comparative Study for Using Deep LSTMs and ARIMA for Imputing Missing Data for Wind Data in the Irish Sea. Preprints 2024, 2024051179. https://doi.org/10.20944/preprints202405.1179.v1
Shoukat, G.; Malekjafarian, A.; Pakrashi, V. A Comparative Study for Using Deep LSTMs and ARIMA for Imputing Missing Data for Wind Data in the Irish Sea. Preprints2024, 2024051179. https://doi.org/10.20944/preprints202405.1179.v1
APA Style
Shoukat, G., Malekjafarian, A., & Pakrashi, V. (2024). A Comparative Study for Using Deep LSTMs and ARIMA for Imputing Missing Data for Wind Data in the Irish Sea. Preprints. https://doi.org/10.20944/preprints202405.1179.v1
Chicago/Turabian Style
Shoukat, G., Abdollah Malekjafarian and Vikram Pakrashi. 2024 "A Comparative Study for Using Deep LSTMs and ARIMA for Imputing Missing Data for Wind Data in the Irish Sea" Preprints. https://doi.org/10.20944/preprints202405.1179.v1
Abstract
Achieving Net Zero emissions target is driving up the need for offshore wind as an alternate energy source. Ireland has the capacity to produce upwards of 30GWof power through offshore wind alone. Wind resource assessments are extremely vital in determining the long term trends of a site. The instruments used for this often suffer breakdowns or miss readings which impacts the long term trend analysis. Wind time series data from Ireland’s Marine Institute is used which is shown to have significant gaps in it’s 20 years of service. Data imputation is necessary to fill in these gaps as accurately as possible. This paper compares LSTMs and ARIMA as two competing methodologies for data imputation. LSTMs are shown to be marginally superior to ARIMA imputation with a mean squared error of 0.45 compared to that of ARIMA of 0.60.
Keywords
Irish Offshore Wind; LSTM; Renewable Energy; ARIMA; Data Imputation
Subject
Environmental and Earth Sciences, Other
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.