Computation for Reinforcement Learning at the Mobile Edge Network.

Wireless Mobile Edge Computing (MEC) is one of several promising models emerging in recent years. A wireless powered MEC network is researched in this paper. The proposed online offload framework based on deep reinforcement learning (DROO) draws lessons from the previous offload experience. As such,...

Descripción completa

Detalles Bibliográficos
Publicado en:SHS Web of Conferences Vol. 144; pp. 1 - 6
Autor principal: Zhao, Zixu
Formato: Artículo
Publicado: EDP Sciences 8/26/022
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=158850593&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 158850593
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        24165182
        FT5R
      jtl: SHS Web of Conferences
      issn: 24165182
      maglogo: N
    pubinfo:
      dt: 8/26/022
      vid: 144
      pid: 76090
      pub: EDP Sciences
    artinfo:
      ui:
        158850593
        10.1051/shsconf/202214403016
      ppf: 1
      ppct: 5
      formats:
      tig:
        atl: Computation for Reinforcement Learning at the Mobile Edge Network.
      aug:
        au: Zhao, Zixu
        affil: School of Electrical and Information engineering, Northeast Agriculture University, Harbin, Heilongjiang province, China, 150006
      sug:
      ab: Wireless Mobile Edge Computing (MEC) is one of several promising models emerging in recent years. A wireless powered MEC network is researched in this paper. The proposed online offload framework based on deep reinforcement learning (DROO) draws lessons from the previous offload experience. As such, it fulfills the need to solve complex problems like MIP. The computational complexity will not surge with the increase of network size. DROO decomposes the original optimization problem into a secondary problem from design to unloading decision and a resource allocation sub-problem. It is suitable for the space without interruption, and there is no need to discretize the channel gain, so as to avoid the disaster caused by the problem of dimension. By studying the simulation results, the DROO algorithm is found that it can achieve almost perfect performance by designing and calculating the method at the current stage, but it also needs to reduce CPU execution latency by at least one order of magnitude, so as to ensure that the realtime system optimization is fading. It is really feasible to use MEC networks when wirelessly powered in the environment.
      pubtype: Conference Proceedings
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2022
    holdings:
      @attributes:
        islocal: N