Performance Enhancement of Multipath TCP for Wireless Communications With Multiple Radio Interfaces

Abstract

Multipath TCP (MPTCP) allows a TCP connection to operate across multiple paths simultaneously and becomes highly attractive to support the emerging mobile devices with various radio interfaces and to improve resource utilization as well as connection robustness. The existing multipath congestion control algorithms, however, are mainly loss-based and prefer the paths with lower drop rates, leading to severe performance degradation in wireless communication systems where random packet losses occur frequently. To address this challenge, this paper proposes a new mVeno algorithm, which makes full use of the congestion information of all the subflows belonging to a TCP connection in order to adaptively adjust the transmission rate of each subflow. Specifically, mVeno modifies the additive increase phase of Veno so as to effectively couple all subflows by dynamically varying the congestion window increment based on the receiving ACKs. The weighted parameter of each subflow for tuning the congestion

Seamless Multimedia Delivery Within a Heterogeneous Wireless Networks Environment: Are We There Yet?

“…Thus, the MPTCP congestion control mechanism might be trigger when not needed and this may cause sever performance degradation. To overcome this situation, Dong et al [192] propose mVeno, an enhanced MPTCP congestion control mechanism for concurrent multipath transfer over wireless networks. mVeno makes use of the fluid flow model and utility theory to model the relationship between the sending rate and the end-to-end packet loss rate.…”

Reducing transport latency for short flows with multipath TCP

“…The congestion control algorithm of MPTCP is responsible for adaptively adjusting the transmission rate of each subflow in an attempt to shift traffic from more congested paths to less congested ones, thus improving the throughput and link utilization. So far, several MPTCP congestion control algorithms have been proposed: LIA (Linked Increases Algorithm (Wischik et al, 2011)), OLIA (Opportunistic Linked-Increases Algorithm (Khalili et al, 2013)), Balia (Balanced Linked Adaptation (Peng et al, 2016)), wVegas (Weighted Vegas (Cao et al, 2012)) and mVeno (Dong et al, 2016).…”

“…The congestion window increasement is calculated according to the network condition of all the subflows belonging to an MPTCP connection rather than one in the regular TCP. Several approaches to handle this issue are available, such as, LIA (Linked Increases Algorithm (Wischik et al, 2011)), OLIA (Opportunistic LIA (Khalili et al, 2013)), Balia (Balanced LIA (Peng et al, 2016)), wVegas (Weighted Vegas (Cao et al, 2012)) and mVeno (Dong et al, 2016). Coupled congestion control only applies to the increase phase of the congestion avoidance state, specifying how the congestion window inflates upon receiving an acknowledgement.…”

(PU)2M2: A potentially underperforming‐aware path usage management mechanism for secure MPTCP‐based multipathing services

“…When there are a great number of O 3 packets held by the constrained receiver buffer, MPTCP will experience severe receiver buffer blocking (RB 2 LOC) problem. 10 Recently, many MPTCP studies have concentrated their efforts on the packet reordering and RB 2 LOC issues [11][12][13][14][15][16] ; however, to the best of our knowledge, the current researches mostly utilize the regular TCP operations to detect a failure-prone path or an underperforming path.…”

“…10 Recently, many MPTCP studies have concentrated their efforts on the packet reordering and RB 2 LOC issues [11][12][13][14][15][16] ; however, to the best of our knowledge, the current researches mostly utilize the regular TCP operations to detect a failure-prone path or an underperforming path. Unfortunately, the standard MPTCP scheduler allocates traffic over all available paths, without considering that asymmetric paths with different delay characteristics may lead to the out-of-order (O 3 ) packet arrival problem.…”