A novel cost-distortion optimization framework for video streaming over differentiated services networks

This paper presents a novel framework for streaming video over a Differentiated Services (DifPjew) network that jointly considers video source coding. packet classification and error concealment within the scope o f costdistortion optimization. Our formulation incorporates the random network delay for each packet into the calculation of the probability of packet loss and manages the end-to-end packet delay by selecting the encoding parameten and packet priority. We formulate two approaches to evaluate the performance o f the proposed framework: a minimum distortion aooroach and a minimum cost aooroach. in level for each packet. Different DS levels result in different QoS levels. such as different packet loss rate and network delay. In this paper, we propose a novvel framework for the joint adaptation of source coding and packet priorily to maximize the system periormance. Our formulation incorporates the random network delay for each packet into the calculation of the probability o f packet loss and manages the end-to-end packet delay by selecting the encoding parameters and packet priority. The aim is to minimize the end-to-end distortion subject to cost constraints, or, alternatively, lo minimize the overall cost given end-to-end distortion constraints. This work i s an extension o f the work in [5 ] which considered constant network delay. to cost &“aints, or to minimize the total cost subject to &d. Wend distortion constraints. Simulation results demonstrate the advantage o f jointly adapting the source d i n g and packet classification.