Neighborhood-centric congestion control for multihop wireless mesh networks

摘要: Complex interference in static multihop wireless mesh networks can adversely affect transport protocol performance. Since TCP does not explicitly account for this, starvation and unfairness result from the use of over such networks. In this paper, we explore mechanisms achieving fair efficient congestion control First, design an AIMD-based rate-control called Wireless Control Protocol (WCP), which recognizes that is a neighborhood phenomenon, node-local one, appropriately reacts to congestion. Second, distributed rate controller estimates available capacity within each divides contending flows, scheme call with Capacity estimation (WCPCap). Using analysis, simulations, real deployments, find our designs yield rates are both efficient. WCP assigns inversely proportional number bottlenecks flow passes through while remaining extremely easy implement. An idealized version WCPCap max-min fair, whereas practical implementation achieves 15% optimal still being amenable implementation.