Deep Reinforcement Learning for Edge-DASH-Based Dynamic Video Streaming

Dynamic Adaptive Streaming over HTTP (DASH) is a promising solution to enhance the Quality of Experience (QoE) of mobile video services. In this paper, we consider an Edge-DASH scenario where two problems of Bitrate Allocation (BrA) and user-to-server allocation (USA) have been jointly formulated. Then, we exploit Deep Reinforcement Learning (DRL) algorithm to solve the USA problem and select the streaming point for users, which can be streaming from the Edge, Macro layer or cloud, and deliver the users the most appropriate bitrate respecting the QoE by solving the BrA problem. In the simulation results, we have demonstrated that our Deep Deterministic Policy Gradient (DDPG) outperforms the traditional solution in terms of bitrate allocation.