Decreasing delay variation in multimedia applications in single-hop wireless

  • Mobasheri, M.; 
  • Kim, Y.; 
  • Lee, H.-G.; 
  • Dehghan, M.; 
  • Takhtfooladi,
Citations

SCOPUS

0

초록

In this paper a sender wants to transmit delay sensitive packets to a base station in a single-hop wireless network. Packets arrival to the sending buffer of the sender is Constant Bit Rate (CBR) for audio packets. It is assumed that the transmission energy of the sender is harvested from the environment and its level is random. Channel Signal to Noise Ratio (SNR) levels determine the channel state in different time steps. In order to sequential decision making with the goal of minimizing the delay of the packets in the sending queue in nondeterministic environment, variancepenalized Markov Decision Process model is used. Because of unknown state transition probability of the system, Reinforcement learning (RL) approach is used to optimize the sender's decisions. The simulation results show the approach in comparison RL for minimizing only the delay has less delay variations but the delay is more. © 2017 Association for Computing Machinery.

키워드

Delay; Delay variations; Multimedia; Reinforcement learning; Wireless network
제목
Decreasing delay variation in multimedia applications in single-hop wireless
저자
Mobasheri, M.; Kim, Y.; Lee, H.-G.; Dehghan, M.; Takhtfooladi,
DOI
10.1145/3145511.3145516
발행일
2017-08-13
유형
Conference Paper
저널명
ACM International Conference Proceeding Series
페이지
46 ~ 49