Reducing the Overhead of View-Upload Decoupling in Peer-to-Peer Video On-Demand Systems

View-upload decoupling (VUD) has become a novel and effective strategy in balancing the supply and demand of bandwidth resources in peer-to-peer (P2P) live streaming systems. In this paper, we investigate the strategy of migrating the existing VUD design from live streaming to P2P video on-demand (VoD) systems. To address the immediate concern of the huge overhead while applying VUD to P2P VoD, we formulate the problem into an optimization problem aiming at minimizing the total overhead induced by VUD, which proves to be a 0-1 integer programming problem. Due to the intractability of this NP-hard problem, we propose a simple yet effective heuristic water-leveling algorithm to balance the supply and demand of bandwidth resources among the system while reducing VUD overhead. Finally, numerical results are presented to demonstrate the efficacy of our overhead-aware VUD design for P2P VoD systems.