PRR Is Not Enough
PRR Is Not Enough
复制标题
PRR 还不够
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
P. Levis
中科院分区：
文献类型：
--
作者：
K. Srinivasan;Maria A. Kazandjieva;Mayank Jain;P. Levis
研究了无线信道突发性对传输控制协议的影响。我们从麻省理工学院的802.11b Roofnet和Intel Berkeley的802.15.4 Mi-Range测试床上测量了单跳链路上的TCP吞吐量。我们观察到，具有相同分组接收率(PRR)的链路具有高达320%的吞吐量变化。我们fi发现吞吐量的差异伴随着链路突发的差异。使用Gilbert-Elliott模型，我们计算了参数µ作为突发性的度量。结果表明，对于超大fi数据道，一个简单的二阶fit就可以将吞吐量估计误差降低50%.对于更一般的fit，相对于Prr和µ，估计误差减少了60%-99%。我们发现，虽然µ具有很好的演绎质量，但相应的吉尔伯特-埃利奥特模型对于模拟来说并不准确：经验链路的fi吞吐量值可能与基于吉尔伯特-埃利奥特模型的相应模拟链路的吞吐量值相差高达80%。这些结果有助于更好地了解无线网络性能出现巨大差异的根本原因。
We study the effects of wireless channel burstiness on TCP. We measure TCP throughput over single-hop link traces from MIT’s 802.11b Roofnet and Intel Berkeley’s 802.15.4 Mi-rage testbeds. We observe that links with the same packet reception ratio (PRR) have throughput variations of up to 320%. We find that differences in throughput are accompanied by differences in link burstiness. Using the Gilbert-Elliott model, we compute the parameter µ as a measure of burstiness. We show that for sufficiently large data traces, a simple second-order fit over both PRR and µ lowers the estimation error of TCP throughput by 50%. The estimation error reduces by 60%-99% for a more general fit over PRR and µ . We find that while µ has good deductive quality, the corresponding Gilbert-Elliott model is not accurate for simulation: TCP throughput values from empirical links and their corresponding simulated links based on the Gilbert-Elliott model can differ by up to 80%. These results help develop a better understanding of the underlying causes for the wide variations seen wireless network performance.