PROJECT TITLE :

Congestion Control for Web Real-Time Communication - 2017

ABSTRACT:

Applications requiring real-time communication (RTC) between Internet peers are ever increasing. RTC requires not solely congestion management but also minimization of queuing delays to produce interactivity. It's known that the well-established transmission control protocol congestion control is not appropriate for RTC thanks to its retransmissions and in-order delivery mechanisms, that induce vital latency. During this paper, we have a tendency to propose a unique congestion control algorithm for RTC, that is based on the main idea of estimating-employing a Kalman Filter-the end-to-end one-approach delay variation which is experienced by packets traveling from a sender to a destination. This estimate is compared with a dynamic threshold and drives the dynamics of a controller located at the receiver, that aims at maintaining queuing delays low, while a loss-based controller located at the sender acts when losses are detected. The proposed congestion control algorithm has been adopted by Google Chrome. In depth experimental evaluations have shown that the algorithm contains queuing delays whereas providing intra and inter protocol fairness together with full link utilization.