A congestion control scheme based on probabilistic packet acceptance and drop in delay‐tolerant networks

摘要: Summary Message replication is often used to improve the delivery ratio in delay-tolerant networks because of short-lived wireless connectivity environment. However, packet may easily incur large resource consumption and finally result network congestion. This paper proposes a probabilistic acceptance drop algorithm (PAD), which adaptively controls congestion for networks. In PAD algorithm, queue length input/output rate are combined detect Based on state, each node determines probability accepting or dropping packets obtain good trade-off between high low overhead. Furthermore, based birth–death model, we construct continuous-time Markov chain analyze packet. Theory analysis simulation results show that increases by more than 130% with least Meanwhile, it also achieves shortest average end-to-end delay when buffer severely limited. Copyright © 2015 John Wiley & Sons, Ltd.