【24h】

An Advanced Exponential Max-Min Kelly Control

机译:先进的指数最大-最小凯利控制

获取原文

摘要

EMKC is an explicit congestion control algorithm which is designed for high bandwidth delay product (BDP) networks. Although delay-independence is an appealing characteristic, the EMKC system developed in exhibits undesirable equilibrium properties and slow fairness convergence behavior. To overcome these drawbacks, we propose a new method called AEMKC (Advanced Exponential Max-Min Kelly Control). In this paper, we investigate AEMKC, prove its stability with heterogeneous delay, study the convergence behavior of AEMKC, and also examine how to implement AEMKC flows briefly. Extensive simulations confirm that AEMKC eliminates stationary packet loss while speeding up the fairness convergence rate. Simulations also show that AEMKC preserves the good properties of EMKC, such as delay-independent stability and max-min fairness in steady state.
机译:EMKC是一种显式的拥塞控制算法,专门用于高带宽延迟乘积(BDP)网络。尽管延迟独立性是一个吸引人的特征,但开发的EMKC系统却显示出不良的平衡特性和缓慢的公平收敛行为。为了克服这些缺点,我们提出了一种称为AEMKC(高级指数最大-最小凯利控制)的新方法。在本文中,我们对AEMKC进行了研究,证明了其具有异构延迟的稳定性,研究了AEMKC的收敛行为,并简要介绍了如何实现AEMKC流程。大量的仿真证实,AEMKC消除了固定的数据包丢失,同时加快了公平收敛速度。仿真还表明,AEMKC保留了EMKC的良好特性,例如独立于延迟的稳定性和稳态下的最大-最小公平性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号