Demo abstract: Context-aware video streaming with Q-learning for MEC-enabled cellular networks
Xiang Zhou, Zheng Chang, Chuanhao Sun, Xi Zhang · 2018
With the proliferation of video streaming service, how to enhance user Quality of Experience (QoE) against the uneven video quality in highly dynamic networks has become a growing concern. Compared with the common solutions in which video streaming adaptation algorithms are implemented on the client-side, we proposed an MEC-side (Mobile Edge Computing) context-aware Q-leaning based video streaming approach to overcome client-driven solutions' weakness of competing behavior and difficulty in enforcing management policies. A working prototype testbed is built by deploying our video streaming platform on an MEC server (close to commercial eNBs) at a real 4G LTE network. Experiment results show our proposed approach adapts better to network variation.