MPTCP Is Not Pareto-Optimal: Performance Issues and a Possible Solution
By R. Khalili, Nicolas Gast, M. Popovic, U. Upadhyay, J. L. Boudec. IEEE/ACM Transactions on Networking, 2013
371 citations recorded by the source corpus.
Subfields: Computer Networks and Communications, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/f841671a75a2fafd5d3842f5d62a5755ad2ddd96
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
- Quentin De Coninck
- Olivier Bonaventure
- Kanak B. Agarwal
- John B. Carter
- Aditya Akella
- D. Towsley
- Christoph Paasch
- Eric Rozner
In Electrical and Electronic Engineering
- Quentin De Coninck
- Olivier Bonaventure
- Aditya Akella
- D. Towsley
- Christoph Paasch
- Rayadurgam Srikant
- Srisankar S. Kunniyur
Citations in the corpus
- Multipath QUIC: Design and Evaluation (2017, background): “Several multipath congestion control schemes have been proposed [27, 38, 48].”
- A measurement-based study of MultiPath TCP performance over wireless networks (2013, methodology): “These studies have resulted in a number of changes in the controller [14,19,32], all in an attempt to provide better fairness and better throughput in the presence of fairness constraints.”
- Presto: Edge-based Load Balancing for Fast Datacenter Networks (2015, methodology): “Ultimately, we found that Mellanox mlx_en4 driver version 2.2, MPTCP version 0.88 [42], subflow count set to 8, OLIA congestion control algorithm [35], and con-figured buffer sizes as recommended by [35, 46, 53] gave us the best trade-offs in terms of throughput, latency, loss and stability.”
- Experimental evaluation of multipath TCP schedulers (2014, methodology): “Finally, the Olia congestion control [10] is used.”