Anomaly-aware adaptation approach for self-adaptive cyber-physical system of systems using reinforcement learning강화학습 기반 자가 적응 사이버 물리 시스템 오브 시스템즈의 변칙 고려 적응 기법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 58
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorBae, Doo-Hwan-
dc.contributor.advisor배두환-
dc.contributor.authorCho, Eunho-
dc.date.accessioned2023-06-26T19:31:30Z-
dc.date.available2023-06-26T19:31:30Z-
dc.date.issued2022-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997594&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/309538-
dc.description학위논문(석사) - 한국과학기술원 : 전산학부, 2022.2,[iv, 31 p. :]-
dc.description.abstractA cyber-physical system of systems (CPSoS) is a system composed of multiple constituent systems that interact with both physical and cyber environments. Self-adaptivity is essential for CPSoS because it works on both cyber and physical uncertainties in various environments. Two obstacles to achieving self-adaptive CPSoS are time constraints and system anomalies. An adaptation should be processed within a certain period and consider anomalies caused by system changes due to mechanical faults, cyber-attacks, or emergent behaviors. However, since existing adaptation approaches cannot fully handle both aspects, this paper proposes an advanced approach, A$^4$, for a self-adaptive system that can handle known anomalies without enormous time in runtime. This approach learns the known anomalies before runtime and mitigates their impact when they are detected. The research evaluated the A$^4$ approach for virtual and physical CPSoS and showed that A$^4$ is more efficient than other approaches.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.titleAnomaly-aware adaptation approach for self-adaptive cyber-physical system of systems using reinforcement learning-
dc.title.alternative강화학습 기반 자가 적응 사이버 물리 시스템 오브 시스템즈의 변칙 고려 적응 기법-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전산학부,-
dc.contributor.alternativeauthor조은호-
Appears in Collection
CS-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0