Impact of fairness on Internet performance

By Thomas Bonald, Laurent Massoulié. Measurement and Modeling of Computer Systems, 2001

478 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/c0eb4819c06a13f2395c6ab6751a3fad1d6d1fb4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

The impact of imperfect scheduling on cross-Layer congestion control in wireless networks (2006, background): “Previous results on the stability region of congestion control typically adopt a time-scale separation assumption [21], [26]–[28], which assumes that the rate allocation perfectly solves (1) at each time instant .”
Multi-Path TCP: A Joint Congestion Control and Routing Scheme to Exploit Path Diversity in the Internet (2006, methodology): “Then we can use the same type of analysis in [2] and show the following result.”
Joint rate control and scheduling in multihop wireless networks (2004, background): “Because the iteration (6) takes time to converge, we can expect that this assumption will better capture systems transferring “longer” files [17].”
Network Optimization and Control (2008, methodology): “in [89] for max-min congestion controllers and by Bonald and Massoulie in [90].”
pFabric: minimal near-optimal datacenter transport (2013, background): “Here, stability is in the stochastic sense meaning that the network may be unable to keep up with flow arrivals even though the average load on each link is less than its capacity [10].”
The Price of Fairness (2011, background): “Bonald and Massoulié (2001) introduce a number of network configurations where it is possible to derive performance results for proportional fairness, yet use simulation to assess max-min fairness.”
An Axiomatic Theory of Fairness in Network Resource Allocation (2009, background): “More recently, α-fair utility functions have been connected to divergence measures [9], and in [10], [11], the parameter α was viewed as a fairness measure in the sense that a fairer allocation is one that is the maximizer of an αfair utility function with larger α — although the exact role”
A tutorial on cross-layer optimization in wireless networks (2006, background): “The use of such utility functions is common in the congestion control literature to model fairness, since with different utility functions the rate allocations that maximize the total system utility can be mapped to a range of fairness objectives [35], [36].”
Layering as Optimization Decomposition: A Mathematical Theory of Network Architectures (2007, background): “For problem (121), it is shown [7], [94], [29], [161] that the stochastic stability region is the interior of feasibility rate region formed by the fixed link capacities, i.”
Fairness in Multi-Agent Sequential Decision-Making (2014, background): “The notion of maximin fairness is also widely used in the field of networking, such as bandwidth sharing, congestion control, routing, load-balancing and network design [1, 9].”
Statistical bandwidth sharing: a study of congestion at flow level (2001, methodology): “[23] L. Massouli´e and J.W. Roberts.”
The war between mice and elephants (2001, methodology): “We also assume Reno-family TCP ﬂows, however, most of the analysis can also apply to other versions of TCP. Due to space limitation, we omit a detailed description of the TCP congestion control algorithm.”
Scheduling distributed applications: the SimGrid simulation framework (2003, background): “A number of recent eorts in network research have tackled the problem of finding models for bandwidth-sharing [30, 5 ]. The typically approach is to make an analogy with fluids in pipes and to ignore the granularity of packets in data transfers, or flows.”
On the Complexity of Scheduling in Wireless Networks (2006, methodology): “Motivated by the works on fair resource allocation in wireline networks [16, 26, 3 , 35], researchers have also incorporated congestion control into the cross-layer optimization framework [4, 19, 21, 33, 28, 36, 24].”
The impact of imperfect scheduling on cross-layer rate control in wireless networks (2005, background): “Previous works for wireline networks have shown that, by allocating data rates to the users according to some fairness criteria, the largest possible stability region can be achieved [16].”