Context-aware adaptive data scheduling algorithm for P2P streaming systems

In mesh-based Peer-to-Peer media streaming systems, media contents are always divided into different data segments and stored in different peers. These segments are then streamed from multiple senders to a receiver. The receiver needs to coordinate the senders by specifying a transmission schedule for each segment. Therefore, the scheduling algorithm, which is in charge of coordinating data received from multiple peers, is the key factor for users' perception of video quality. In order to improve the overall performance of streaming systems, the Context-aware Adaptive (CAA) scheduling algorithm is proposed in this paper. In CAA algorithm, priorities for data segments are defined based on context information and the neighbors' bandwidth is dynamically evaluated. Then, the CAA algorithm calculates the order and direction of data segments from neighbors, according to context information such as priority of segments, current utilization of senders and the network capacity. Simulation results show that the proposed CAA scheduling algorithm requires smaller startup delays, and enhances the peer's average throughput. What's more, it achieves more balanced load distribution across peers than some conventional scheduling algorithms, and also improves the continuity index.