• 대한전기학회
Mobile QR Code QR CODE : The Transactions of the Korean Institute of Electrical Engineers
  • COPE
  • kcse
  • 한국과학기술단체총연합회
  • 한국학술지인용색인
  • Scopus
  • crossref
  • orcid
Title Decomposed Artificial Neural Networks for Analyzing the Electricity Market with Incomplete Information
Authors 이광호(Kwang-Ho Lee)
DOI https://doi.org/10.5370/KIEE.2020.69.4.560
Page pp.560-565
ISSN 1975-8359
Keywords Artificial Neural Networks; Electricity Market; Incomplete Information; Oligopoly; Nash Equilibrium; Decomposed Structure
Abstract This paper proposes an decomposed structure of artificial neural networks (NN) for analyzing electricity market for calculating equilibrium. We attempted to separate the neural network structure into small pieces by drawing a state hidden inside the integrated structure. Then the NN takes a longer time to learn, but if there is uncertainty in the information handled by the ANN, the decomposed NN proposed in this study is meaningful. In particular, if the accuracy of the NN is a concern due to incomplete information, the advantages of decomposed NN become more prominent.