In this paper we revisit the interaction between baseRTT estimation and congestion control action. We develop a simple AIMD-based scheme that allows network buffers to drain and thus demonstrate in a constructive manner that, with proper design, it is indeed possible for flows traversing a bottleneck link to estimate their base RTT reliably
TCPs congestion control was traditionally based on packet losses. This approach leads to an ineffici...
TCPs congestion control was traditionally based on packet losses. This approach leads to an ineffici...
Additive increase multiplicative decrease (AIMD) algorithm is the prevailing algorithm for congestio...
In this paper we revisit the interaction between baseRTT estimation and congestion control action. ...
In this paper we revisit the interaction between baseRTT estimation and congestion control action. ...
The thesis begins with a short review of TCP and new congestion control schemes in Chapter 2. Follow...
Our interest in the paper is investigating whether it is feasible to make modifications to the TCP ...
International audienceWe propose a new RTT based congestion control scheme. The key idea is to use s...
We argue that, in the absence of explicit feedback, delay-based algorithms become the preferred appr...
We argue that, in the absence of explicit feedback, delay-based algorithms become the preferred appr...
Loss-based congestion control protocols such as TCP CUBIC can unnecessarily fill router buffers addi...
Traditional loss-based TCP congestion control (CC) tends to induce high queuing delays and perform b...
We introduce a model of the Relentless Congestion Control proposed by Matt Mathis. Relentless Conges...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Abstract—Two considerable problems for designing a new protocol in high bandwidth delay product (BDP...
TCPs congestion control was traditionally based on packet losses. This approach leads to an ineffici...
TCPs congestion control was traditionally based on packet losses. This approach leads to an ineffici...
Additive increase multiplicative decrease (AIMD) algorithm is the prevailing algorithm for congestio...
In this paper we revisit the interaction between baseRTT estimation and congestion control action. ...
In this paper we revisit the interaction between baseRTT estimation and congestion control action. ...
The thesis begins with a short review of TCP and new congestion control schemes in Chapter 2. Follow...
Our interest in the paper is investigating whether it is feasible to make modifications to the TCP ...
International audienceWe propose a new RTT based congestion control scheme. The key idea is to use s...
We argue that, in the absence of explicit feedback, delay-based algorithms become the preferred appr...
We argue that, in the absence of explicit feedback, delay-based algorithms become the preferred appr...
Loss-based congestion control protocols such as TCP CUBIC can unnecessarily fill router buffers addi...
Traditional loss-based TCP congestion control (CC) tends to induce high queuing delays and perform b...
We introduce a model of the Relentless Congestion Control proposed by Matt Mathis. Relentless Conges...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Abstract—Two considerable problems for designing a new protocol in high bandwidth delay product (BDP...
TCPs congestion control was traditionally based on packet losses. This approach leads to an ineffici...
TCPs congestion control was traditionally based on packet losses. This approach leads to an ineffici...
Additive increase multiplicative decrease (AIMD) algorithm is the prevailing algorithm for congestio...