延迟容忍网络中的拥塞避免优化算法仿真

发布时间：2018-10-05 08:23

【摘要】：研究延迟容忍网络中的拥塞避免优化算法。在延迟容忍网络中采用托管传输机制,造成网络资源受限性耗尽,形成网络拥塞。传统的TCP拥塞控制算法在控制端存在快速反馈节点的前提下,采用慢开始、快重传的拥塞控制策略,但是容忍网络中不存在固定的控制端,链路上下带宽不对称,很难建立准确的拥塞回执,因此造成控制效果不佳。为了避免上述缺陷,提出了一种基于网络拥塞状态参数优化的延迟容忍网络中的拥塞避免优化算法。根据TCP协议的数据反馈机制,能够估计延迟容忍网络中的带宽。根据传输数据等待时间差值,能够计算待传输数据长度。利用网络拥塞状态参数优化方法,能够实现延迟容忍网络中的拥塞避免优化。实验结果表明,利用本文算法进行延迟容忍网络拥塞避免优化,能够提高数据传输的效率。
[Abstract]:The congestion avoidance optimization algorithm in delay tolerant networks is studied. In the delay tolerance network, the managed transmission mechanism is adopted, which results in the network resource depletion and network congestion. The traditional TCP congestion control algorithm adopts a slow start and fast retransmission congestion control strategy on the premise of fast feedback nodes at the control end, but there is no fixed control end in the tolerant network, and the link bandwidth is asymmetric. It is difficult to establish accurate congestion receipt, so the control effect is not good. In order to avoid the above shortcomings, a congestion avoidance optimization algorithm based on network congestion state parameter optimization is proposed for delay tolerance networks. According to the data feedback mechanism of TCP protocol, the bandwidth of delay tolerant network can be estimated. The length of the data to be transmitted can be calculated according to the difference of the waiting time of the transmitted data. Congestion avoidance optimization in delay-tolerant networks can be realized by optimizing congestion state parameters. Experimental results show that the proposed algorithm can improve the efficiency of data transmission by optimizing the delay tolerance network congestion avoidance.
【作者单位】：开封大学;
【分类号】：TP393.06

【参考文献】