Revolving Indexed Edge Buffering Architecture in Staged On-Demand Streaming over the Internet: Design and Analysis

On-demand streaming from a remote server through best-effort Internet poses several challenges because of network losses and variable delays. We provide a comprehensive review and develop taxonomy of current methods to enhance the delivery quality of multimedia streaming. We then develop new delivery models for a distributed architecture in which video is streamed from a remote server to an edge server where the video is buffered and then streamed to the client through a last mile connection. The model uses a novel revolving indexed buffering mechanism at the edge server and employs selective retransmissions of lost packets between the remote and edge servers for a best-effort recovery of the losses. The performance of buffer management and retransmission policies at the edge server is modeled and assessed using a probabilistic analysis of the streaming process and system simulations. The influence of different endogenous control parameters on the quality of stream received by the client is studied. Calibration curves on the QoS metrics for different network conditions have been obtained using simulations. These could be used to set the values of the different endogenous control parameters for specific QoS in real-time streaming operations. A methodology to benchmark transmission characteristics using real-time traffic data is developed to enable effective decision making on edge server buffer allocation and management strategies.