In this paper, we propose a systematic solution to the problem of cross-layer optimization for delay-sensitive media transmission over time-varying wireless channels as well as investigate the structures and properties of this solution, such that it can be easily implemented in various multimedia systems and applications. Specifically, we formulate this problem as a finite-horizon Markov decision process (MDP) by explicitly considering the users' heterogeneous multimedia traffic characteristics (e.g. delay deadlines, distortion impacts and dependencies etc.), time-varying network conditions as well as, importantly, their ability to adapt their cross-layer transmission strategies in response to these dynamics. Based on the heterogeneous characteristics of the media packets, we are able to express the transmission priorities between packets as a new type of directed acyclic graph (DAG). This DAG provides the necessary structure for determining the optimal cross-layer actions in each time slot: the root packet in the DAG will always be selected for transmission since it has the highest positive marginal utility; and the complexity of the proposed cross-layer solution is demonstrated to linearly increase w.r.t. the number of disconnected packet pairs in the DAG and exponentially increase w.r.t. the number of packets on which the current packets depend on. The simulation results demonstrate that the proposed solution significantly outperforms existing state-of-the-art cross-layer solutions. Moreover, we show that our solution provides the upper bound performance for the cross-layer optimization solutions with delayed feedback such as the well-known RaDiO framework.
DeepStream: Prototyping Deep Joint Source-Channel Coding for Real-Time Multimedia Transmissions
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Xidian University（西安电子科技大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；China Academy of Information and Communications Technology（中国信息通信研究院）
Actor-Critic Scheduling for Path-Aware Air-to-Ground Multipath Multimedia Delivery
Institute of Information Science and Technologies (ISTI), CNR（意大利国家研究委员会信息科学与技术研究所）；CNIT - National Inter-University Consortium for Telecommunications（全国大学间电信联盟）；University of Pisa（比萨大学）
