eduzhai > Applied Sciences > Engineering >

Multiagent Reinforcement Learning based Energy Beamforming Control

  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Ultra low power devices make far-field wireless power transfer a viableoption for energy delivery despite the exponential attenuation. Electromagneticbeams are constructed from the stations such that wireless energy isdirectionally concentrated around the ultra low power devices. Energybeamforming faces different challenges compare to information beamforming dueto the lack of feedback on channel state. Various methods have been proposedsuch as one-bit channel feedback to enhance energy beamforming capacity, yet itstill has considerable computation overhead and need to be computed centrally.Valuable resources and time is wasted on transfering control information backand forth. In this paper, we propose a novel multiagent reinforcementlearning(MARL) formulation for codebook based beamforming control. It takesadvantage of the inherienntly distributed structure in a wirelessly powerednetwork and lay the ground work for fully locally computed beam controlalgorithms. Source code can be found atthis https URL.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×