On adaptive live streaming in mobile cloud computing environments with D2D cooperation

Abstract

The gap between the traffic demand and the link capacity, along with time-varying link conditions, results in poor service quality of video streaming services over the mobile networks. Leveraging the mobile cloud computing and wireless Device to Device (D2D) technology, we propose and discuss a framework to improve the quality of video services in a special scenario that adjacent mobile devices desire to synchronously receive a live content stream. Traditionally, these devices are competitors to the expensive and variation server to device interfaces, even they request for the same live stream. The proposed cloud-based live stream server will improve the Dynamic Adaptive streaming over HTTP (DASH) service by computing and transcoding the original stream segment according to the accumulated bandwidth of the devices' group, then divide the trans-coded stream segment into fragments for each device to fetch. After the devices received the fragments, every device can get the whole segment by exchanging the fragments through the free short-range D2D interface. This mechanism could provide higher resolution live streaming with less expense by the cooperation among adjacent mobile devices. The Quality of Experience (QoE) and network utilization will also be improved. We present the scheme in details and our implementation on Android smart-phones to testify the performance.