R. Pan, L. Breslau, B. Prabhakar, and S. Shenker. Approximate fairness through dierential dropping (one page summary). ACM Computer Communication Review, Jan. 2002.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....measurement studies (e.g. 9, 8] is that a small percentage of flows accounts for a large percentage of the tra#c. 8] shows that 9 of the flows between AS pairs account for 90 of the byte tra#c between all AS pairs. For many applications, knowledge of these large flows is probably su#cient. [8, 17] suggest achieving scalable di#erentiated services by providing selective treatment only to a small number of large flows. 9] underlines the importance of knowledge of heavy hitters for decisions about network upgrades and peering. 5] proposes a usage sensitive billing scheme that relies on ....

....monitoring and attack detection, it may su#ce to focus on large flows. Scalable Queue Management: At a smaller time scale, scheduling mechanisms seeking to approximate max min fairness need to detect and penalize flows sending above their fair rate. Keeping per flow state only for these flows [10, 17] can improve fairness with small memory. We do not address this application further, except to note that our techniques may be useful for such problems. For example, 17] uses classical sampling techniques to estimate the sending rates of large flows. Given that our algorithms have better accuracy ....

[Article contains additional citation context not shown here]

R. Pan et al. Approximate fairness through di#erential dropping. Tech. report, ACIRI, 2001.

No context found.

R. Pan, L. Breslau, B. Prabhakar, and S. Shenker. Approximate fairness through dierential dropping (one page summary). ACM Computer Communication Review, Jan. 2002.

....routers, however, as they require the maintenance of per flow state to distinguish, bu#er and schedule the packets of individual flows. This has led researchers to explore trading o# performance for simplicity of implementation, yielding router mechanisms that provide approximate fairness [6,17,16]. An alternate line of research takes an economic approach to congestion management. Following this approach the network attempts to induce users to condition their flows; this avoids the implementation complexity inherent in erecting explicit bandwidth firewalls. Using ideas from economics, ....

R. Pan, L. Breslau, B. Prabhakar, and S. Shenker. Approximate fairness through di#erential dropping. In Submitted, 2001. 26

....are in need of drastically different attention than flows limited by host bu#er sizes. Further, many router algorithms to control per flow bandwidth algorithms have been proposed, and the performance and scalability of some of these algorithm depends on the nature of the flow rates seen at routers [9, 10, 14]. Thus, knowing more about these rates may inform the design of such algorithms. Finally, knowledge about the rates and their causes may lead to better models of Internet tra#c. Such models could be useful in generating simulation workloads and studying a variety of network problems. In this ....

....while we address flow rates from a somewhat di#erent angle, our paper is not the first to study Internet flow rates. A preliminary look at Internet flow rates in a small number of packet traces found the distribution of rates to be skewed, but not as highly skewed as the flow size distribution [14]. This result was consistent with observation in [10] that a small number of flows accounted for a significant number of the total bytes. In recent work, Sarvotham et al. [20] found that a single high rate flow usually accounts for the burstiness in aggregate tra#c. In [2] the authors look at the ....

R. Pan, L. Breslau, B. Prabhakar, and S. Shenker, "Approximate Fairness through Di#erential Dropping," ACIRI Technical Report, 2001. http://www.icir.org/shenker/afd-techreport.ps

....SCOTT SHENKER Abstract. We present a simple, exact algorithm for iceberg queries (identifying in a multidet the items with frequency more than a threshold ) that requires two passes, linear time, and space 1= 1. Introduction In many applications, ranging from network congestion monitoring [5] to data mining [3] and the analysis of web query logs [2] it is often desirable to identify from a very long sequence of symbols (or tuples, or packets) coming from a large alphabet those symbols whose frequency is above a given threshold. Such analysis is sometimes called an iceberg query [3, ....

Rong Pan, Lee Breslau, Balaji Prabhakar, and Scott Shenker, \Approximate Fairness through Dierential Dropping," preprint, 2001.

No context found.

R. Pan, L. Breslau, B. Prabhakar, and S. Shenker, "Approximate fairness through di#erential dropping," Jan. 2002.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC