Adaptive Bitrate Streaming in Wireless Networks with Transcoding at Network Edge Using Deep Reinforcement Learning
Adaptive bitrate (ABR) streaming has been used in wireless networks to deal with the time-varying wireless channels. Traditionally, wireless video is fetched from remote Internet server. However, wireless video streaming from Internet server faces challenges such as congestion and long latency. ABR streaming and video transcoding at the radio access network (RAN) edge have shown the potential to overcome such problem and provided better video streaming service. In the paper, we consider joint computation and communication for ABR streaming based on mobile edge computing (MEC) under time-varying wireless channels. We propose a joint video transcoding and quality adaptation framework for ABR streaming by enabling RAN with computing capability. By modeling the wireless channel as a finite state Markov channel, we formulate the optimization problem as a stochastic optimization problem of joint computational resource assignment and video quality adaptation for maximizing the average reward, which is defined as the tradeoff between user perceived quality of experience and the cost of performing transcoding at edge server. By using deep reinforcement learning (DRL) algorithm, we develop an automatic algorithm to perform the computational resource assignment and video quality adaptation without any prior knowledge of channel statistics. Simulation results using Tensorflow show the effectiveness of the designed MEC-enabled ABR streaming system and DRL algorithm.
|Keywords||Adaptive bitrate streaming, deep reinforcement learning, mobile edge computing, video transcoding, wireless networks|
|Journal||IEEE Transactions on Vehicular Technology|
Guo, Y. (Yashuang), Yu, F.R, An, J. (Jianping), Yang, K. (Kai), Yu, C. (Chuqiao), & Leung, V.C.M. (Victor C. M.). (2020). Adaptive Bitrate Streaming in Wireless Networks with Transcoding at Network Edge Using Deep Reinforcement Learning. IEEE Transactions on Vehicular Technology, 69(4), 3879–3892. doi:10.1109/TVT.2020.2968498