Classification-based Multi-client Video Transmission over Heterogeneous Networks

These Real-time video streaming over networks operates under stringent network resource constraints, with multiple video clients competing for limited network resources. In this paper, we study the problem of bandwidth allocation for video transmission over heterogeneous networks, with multiple video clients connecting to the video server simultaneously and demanding for the video services, and aim to provide the best possible Quality of Service (QoS) under limited bandwidth of both the video server and multiple video clients. We propose a classification-based approach for multi-client video transmission over heterogeneous networks (CMVT). Firstly, the video server detects the available bandwidth of multiple video clients and classifies the clients into different classes. Secondly, the limited export bandwidth of the server is allocated to different video clients using the client classification results and greedy algorithm. Finally, the video server transmits video streams to video clients in different classes through Unicast and clients in the same class through Unicast and forwarding. Experimental results demonstrate that the proposed video transmission method can use the network bandwidth efficiently and provide better video quality to