Emulation of expensive simulation model for operation and maintenance of offshore wind farms

Majumder, Jayanta and Lazakis, Iraklis and Dalgic, Yalcin and Dinwoodie, Iain and Revie, Matthew and McMillan, David; (2015) Emulation of expensive simulation model for operation and maintenance of offshore wind farms. In: State of the Art on Energy Developments. University of the West of Scotland, GBR. ISBN 9781903978528

[img]
Preview
 Text (Majumder-etal-SEEP-2015-simulation-model-for-operation-and-maintenance-of-offshore-wind-farms)
Majumder_etal_SEEP_2015_simulation_model_for_operation_and_maintenance_of_offshore_wind_farms.pdf
Accepted Author Manuscript
Download (764kB)| Preview
    [img]
    Preview
    		 Text (Majumder_etal_SEEP_2015_simulation_model_for_operation_and_maintenance_of_offshore_wind_farms)
    Majumder_etal_SEEP_2015_simulation_model_for_operation_and_maintenance_of_offshore_wind_farms.pdf
    Accepted Author Manuscript
    Download (765kB)| Preview

      Abstract

      As wind farms move deeper offshore to tap into stronger and relentless winds, intense wind and wave conditions pose a great challenge in terms of their operation and maintenance (O&M). There are several factors that determine the profitability of offshore wind farms, and the most critical factors among them are the parameters on allocation of maintenance resources. These parameters interact with environmental factors and make it impossible to estimate profitability using simple formulas. On the other hand, existing simulation models, which describe the behaviour of wind farms by using mathematical models of wind, wave, and their effects on O&M, can be extremely detailed resulting in simulations being computationally very expensive. Depending on the number of scenarios to evaluate, it can take up-to several days to complete the computation. In order to address this difficulty, a statistical model fitting approach has been adopted to emulate the behaviour of the computationally expensive simulator. Neural networks, splines, and decision trees are combined to capture numerical and discrete variables and their influence on availability and profitability. This approach is useful because it allows for quick exploration of the space of operating choices, which would be difficult to achieve by repeated simulations due to their computational expense. The performance results show that the statistical model can evaluate hundreds of scenarios per second, and the approximation error is acceptable.

      Creators(s): Majumder, Jayanta, Lazakis, Iraklis ORCID logoORCID: https://orcid.org/0000-0002-6130-9410, Dalgic, Yalcin, Dinwoodie, Iain ORCID logoORCID: https://orcid.org/0000-0001-9090-1256, Revie, Matthew ORCID logoORCID: https://orcid.org/0000-0002-0130-8109 and McMillan, David ORCID logoORCID: https://orcid.org/0000-0003-3030-4702;
      Item type:Book Section
      ID code:55514
      Keywords:statistical Models, neural networks, decision trees, splines, offshore wind farms, operation and maintenance, Hydraulic engineering. Ocean engineering, Electrical engineering. Electronics Nuclear engineering, Energy Engineering and Power Technology, Management Science and Operations Research
      Subjects:Technology > Hydraulic engineering. Ocean engineering
      Technology > Electrical engineering. Electronics Nuclear engineering
      Department:Faculty of Engineering > Naval Architecture, Ocean & Marine Engineering
      Faculty of Engineering > Electronic and Electrical Engineering
      Strathclyde Business School > Management Science
      Depositing user: Pure Administrator
      Date deposited:10 Feb 2016 10:05
      Last modified:22 Apr 2020 00:20
      Related URLs:
      URI:https://strathprints.strath.ac.uk/id/eprint/55514
      Export data:
      CORE (COnnecting REpositories)