• DocumentCode
    3740434
  • Title

    A Winner Agent in a Smart Grid Simulation Platform

  • Author

    Serkan Ozdemir;Rainer Unland

  • Author_Institution
    DAWIS, Univ. Duisburg-Essen, Essen, Germany
  • Volume
    2
  • fYear
    2015
  • Firstpage
    206
  • Lastpage
    213
  • Abstract
    Local energy production and distributed energy storage facilities will take a leading position in the future smart grid along with the challenge of sustainability. To cope with this, smart grid simulation platforms are needed to analyze the problems of two-way data and energy flow. The Power Trading Agent Competition (Power TAC) provides an open source, smart grid simulation platform to enable various smart grid studies from the perspective of sustainability. Besides, an annual competition is held in which broker agents trade in energy markets to meet their supply and demand. AgentUDE is one of the broker agents competed in the Power TAC 2014 Final. This paper details the trading strategies of AgentUDE, which won the competition using adaptive trading strategies. The paper also analyzes the tournament data from the winner agent´s point of view.
  • Keywords
    "Games","Smart grids","Production","Hidden Markov models","Supply and demand","Power markets","Electric vehicles"
  • Publisher
    ieee
  • Conference_Titel
    Web Intelligence and Intelligent Agent Technology (WI-IAT), 2015 IEEE / WIC / ACM International Conference on
  • Type

    conf

  • DOI
    10.1109/WI-IAT.2015.30
  • Filename
    7397361