<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>29668</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>1</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>image</type>
    <publisherName>Innovation Hub 13, TH Wildau</publisherName>
    <publisherPlace>Wildau</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-12-05</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Simulating Volatile Wind Energy: Stochastic Forward Modeling and Machine Learning</title>
    <abstract language="eng">The transformation of the energy sector is based on the integration of various renewable sources, such as wind and solar energy. One of the key challenges for the integration of these sources into the existing power grid is their erratic and sometimes discontinuous availability (volatility). Wind energy is one of the most relevant sources of CO2 neutral electric energy, but volatile due to fluctuating wind fields on multiple scales. This has already been realized so that senors provide real-time information on the scale of individual wind turbines. However, fore- casting remains an unresolved problem since numerical weather prediction models cannot provide the necessary level of detail. New modeling strategies are required that integrate turbine-scale and meso-scale information for accurate site-specific short-term prediction. Present and forthcoming research aims to incorporate fluctuations on multiple levels of fidelity, depending on the abstraction layer</abstract>
    <identifier type="url">https://ai-science-atlas.innohub13.de/files/pdf/NSGSimulatingVolatileWindEnergyBTUpdf.pdf</identifier>
    <identifier type="url">https://www-docs.b-tu.de/fg-stroemungsmodellierung/public/Klein_poster_KI-Atlas22.pdf</identifier>
    <enrichment key="BTU">an der BTU erstellt / created at BTU</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="Fprofil">1 Energiewende und Dekarbonisierung / Energy Transition and Decarbonisation</enrichment>
    <enrichment key="Fprofil">4 Künstliche Intelligenz und Sensorik / Artificial Intelligence and Sensor Technology</enrichment>
    <author>
      <firstName>Marten</firstName>
      <lastName>Klein</lastName>
    </author>
    <submitter>
      <firstName>Marten</firstName>
      <lastName>Klein</lastName>
    </submitter>
    <author>
      <firstName>Juan Alí</firstName>
      <lastName>Medina Méndez</lastName>
    </author>
    <author>
      <firstName>Heiko</firstName>
      <lastName>Schmidt</lastName>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>AI transfer</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>AI teaching</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>stochastic modeling</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>machine learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>wind energy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>volatility modeling and prediction</value>
    </subject>
    <collection role="institutes" number="3504">FG Numerische Strömungs- und Gasdynamik</collection>
    <collection role="institutes" number="7006">Energie-Innovationszentrum / Scientific Computing Lab</collection>
  </doc>
</export-example>
