Congestion Window Control Research Articles

UNDERSTANDING THE TRADE-OFF IN TCP'S CUBIC WINDOWS CONGESTION: A COMPREHENSIVE ANALYSIS

This study investigates the difficulties of the CUBIC TCP algorithm, focusing on the trade-off between efficiency and fairness in window congestion control. The CUBIC approach, which was devised to optimize high-bandwidth and long-distance networks, is currently widely used as the default TCP congestion control algorithm in Linux and other systems. Our work investigates the dynamics of CUBIC's window expansion, specifically the interaction between the cubic function and the most recent congestion event. We look at how this interplay impacts the distribution of window widths, throughput, round-trip time (RTT), loss rate, and queue size under different network configurations. Keywords: TCP CUBIC, Window Congestion, Efficiency-Fairness Trade-Off, TCP’s Cubic Function.

STOP: Joint send buffer and transmission control for user-perceived deadline guarantee via curriculum guided-deep reinforcement learning

Real-time applications with strict user-perceived deadline requirements, such as cloud virtual reality (VR) gaming and high-frequency trading, have experienced substantial growth in recent years. To ensure the user-perceived deadline at the transport layer, i.e., the network transmission delay and the waiting delay in the send buffer, transmission control scheme plays an important role. While several delay-sensitive transmission control schemes have been proposed, none of them consider the impact of waiting delay in the send buffer. To address this issue, we propose STOP, a joint send buffer and congestion window (CWND) control approach for guaranteeing user-perceived deadline via curriculum-guided deep reinforcement learning. To obtain optimal joint control policy, STOP utilizes a reinforcement learning-based algorithm to jointly adjust the CWND and send buffer with respect to the send buffer state, the network condition and the deadline requirement. Furthermore, to enhance the generalization capability of reinforcement learning-based algorithm, STOP incorporates curriculum learning during the training phase with a difficulty measurer and training scheduler. Extensive experiments in NS-3 indicate that the STOP scheme achieves an overwhelmingly higher average arrival ratio, i.e., around 95% vs. around 0.2%, compared with current prevalent transmission control scheme such as BBR, Cubic and Vegas.

Adaptive Decrease Window for BALIA (ADW-BALIA): Congestion Control Algorithm for Throughput Improvement in Nonshared Bottlenecks

The main design goals of the multipath transmission control protocol (MPTCP) are to improve the throughput and share a common bottleneck link fairly with a single-path transmission control protocol (TCP). The existing MPTCP congestion control algorithms achieve the goal of fairness with single-path TCP flows in a shared bottleneck, but they cannot maximize the throughput in nonshared bottlenecks, where multiple subflows traverse different bottleneck links. This is because the MPTCP is designed not to exceed the throughput of a single-path TCP competing in the bottleneck. Therefore, we believe that MPTCP congestion control should have different congestion window control mechanisms, depending on the bottleneck type. In this paper, we propose an adaptive decrease window (ADW) balanced linked adaptation (BALIA) congestion control algorithm that adaptively adjusts the congestion window decrease in order to achieve better throughput in nonshared bottlenecks while maintaining fairness with the single-path TCP flows in shared bottlenecks. The ADW-BALIA algorithm detects shared and nonshared bottlenecks based on delay fluctuations and it uses different congestion window decrease methods for the two types of bottleneck. When the delay fluctuations of the MPTCP subflows are similar, the ADW-BALIA algorithm behaves the same as the existing BALIA congestion control algorithm. If the delay fluctuations are dissimilar, then the ADW-BALIA algorithm adaptively modulates the congestion window reduction. We implement the ADW-BALIA algorithm in the Linux kernel and perform an emulation experiment that is based on various topologies. ADW-BALIA improves the aggregate MPTCP throughput by 20% in the nonshared bottleneck scenario, while maintaining fairness with the single-path TCP in the shared bottleneck scenario. Even in a triple bottleneck topology, where both types of bottlenecks exist together, the throughput increases significantly. We confirmed that the ADW-BALIA algorithm works stably for different delay paths, in competition with CUBIC flows, and with lossy links.

BELIA: bandwidth estimate‐based link increase algorithm for MPTCP

As a set of extensions to the regular Transmission Control Protocol (TCP), Multipath TCP (MPTCP) enables the multi-homed devices to access one data stream through multiple paths. MPTCP congestion window control is the crucial part of maintaining the fair network resource allocation, especially in the coexist scene of MPTCP applications and regular TCP applications. However, the current MPTCP congestion window control is facing two major problems: (i) the lack of the lost-packet detections, and (ii) the lack of the analysis mechanisms on the through-load relationships. These two problems combined may affect the accuracy of the congestion window allocations and the performance of MPTCP. In this study, the authors propose a bandwidth estimate-based link increase algorithm (BELIA). With the analysis of the link congestion occurrence mechanisms, they utilise a batch filter to estimate the real bandwidth of the links and define the link condition set C r to demonstrate the possibility of the congestion occurrence. For every loss, BELIA decides whether to cut window size off referring to the bandwidth estimates and C r . Hence, they proved that BELIA satisfies three design goals of MPTCP. Moreover, the authors' simulations show that BELIA performs better than some typical MPTCP congestion control algorithms under the same circumstances.

Congestion avoidance algorithm using ARIMA(2,1,1) model-based RTT estimation and RSS in heterogeneous wired-wireless networks

In the past two decades, there has been a fast growth in the heterogeneous wired-wireless network which connects variety of networks such as wired network, wireless network, high speed network and sensor network with the Internet. Since the wired network and wireless network use the different technologies, there is a necessity of developing new protocols or redesigning of existing protocols. Transmission Control Protocol is redesigned to achieve the reliable and effective communication in the heterogeneous wired-wireless network. The basic assumption made in Transmission Control Protocol is that the packet losses are caused by the network congestion but in case of wireless network, the packet losses may be due to temporary link failure, high Bit-Error-Rate etc. Hence the congestion avoidance algorithm of Transmission Control Protocol needs to be redesigned to cope with heterogeneous wired-wireless network. Therefore in this paper, we propose a congestion avoidance algorithm which differentiates the cause of packet losses. The essential components of proposed algorithm are round-trip-time estimation, backlogged packet estimation, channel status notification, loss differentiation algorithm and congestion window control. A round-trip-time estimation using ARIMA(2,1,1) model is proposed in this paper which estimates the sudden changes in the round trip time. It helps us to estimate the backlogged packet and thereby differentiating the congestive packet loss from non-congestive packet loss. In addition, we use the received signal strength of wireless receiver to differentiate the packet losses. Based on the packet loss differentiation, the congestion window size is controlled to avoid the congestion in the network. The proposed algorithm is simulated using network simulator under different network environments. From the simulation results, it is realized that the proposed congestion avoidance algorithm performs well in the heterogeneous wired-wireless network.

On rate limitation mechanisms for TCP throughput: A longitudinal analysis

TCP remains the dominant transport protocol for Internet traffic. It is usually considered to have its sending rate covered by a sliding window congestion control mechanism. However, in addition to this normal congestion control, a number of other mechanisms limit TCP throughput. This paper analyses the extent to which network, host and application settings define flow throughput over time and across autonomous systems. Our study draws on data from a longitudinal study spanning five years of passive traces collected from a single transit link. Mechanisms for this include limiting by application, interference with the TCP window control mechanism and artificial limitations on maximum window sizes by the operating system. This paper uses a large data set to assess the impact of each mechanism. We conclude that more than half of all heavy-hitter inbound traffic remains throttled by constraints beyond network capacity. For this data set, TCP congestion control is no longer the dominant mechanism that moderates throughput.

An effective approach to alleviating the challenges of transmission control protocol

The transmission control protocol (TCP) has contributed to the tremendous success of the Internet but it also faces many challenges which are becoming more and more significant as the network grows. Although numerous congestion control algorithms have been proposed to improve the performance of TCP in heterogeneous networks, designing a congestion control algorithm that could achieve high utilisation, ensure fairness and maintain stability remains a great challenge. A novel congestion control algorithm named fair TCP (FTCP) has been proposed to mitigate these challenges. FTCP mitigates these challenges through the following strategies: First, increase the round trip time (RTT)-fairness by altering TCP's initial congestion control window (cwnd) and adjusting the cwnd's growth rate to make FTCP flows with different RTTs achieve the same throughput. Secondly, balance the transmission efficiency and TCP-friendliness by dynamically adjusting the aggressiveness of FTCP according to the congestion level of the link. Preliminary experimental evaluations verify that FTCP has obvious advantages in transmission efficiency, RTT-fairness and TCP-friendliness comparing to the state-of-the-art congestion control algorithms.

Delay-based Congestion Control for Multipath TCP

A single flow stream could be divided into several sub-flows to be sent across multiple paths. This method obtains obvious advantages against traditional TCP as it maintains higher reliability and makes bettaer use of the network resources. Congestion control algorithm is an essential part to be considered. This paper first reviews the existing multipath TCP congestion control algorithms and then analyzes and formulates the goals and problems need to be achieved and solved. A delay-based congestion control algorithm named Weighted Vegas (wVegas) is provided. Finally, two possible modifications are demonstrated including adjusting the congestion control window according to how far the path is from congestion and redefining the behavior when loss occurs.

The COMMStellation<sup>TM</sup> Satellite Constellation for Broadband Communication System Model in NS-2

This paper presents the evaluation performance of a hybrid satellite constellation network which provides internet access based Transport Control Protocol (TCP). The evaluated satellite network uses the constellation topology operating on Low Earth Orbit (LEO). The COMMStellationTM satellite system implemented using network simulator 2 (NS-2). In this paper, we modified a congestion window control based on TCP Westwood. The results show that the proposed technique reduces end-to-end (E2E) delay of transmitting packets. Hence the number of retransmission packets reduced.

AppTCP: The design and evaluation of application-based TCP for e-VLBI in fast long distance networks

Electric Very Long Baseline Interferometry (e-VLBI) is a typical astronomical interferometry used in radio astronomy. It allows observations of an object that are made simultaneously by many radio telescopes to be combined, emulating a telescope with the size equal to the maximum separation between the telescopes. The main requirements of transporting e-VLBI data are the high and constant transmission rate. However, the traditional TCP and its variants cannot meet these requirements. In an effort to solve the problem of transporting e-VLBI data in fast long distance networks, we propose an application-based TCP (AppTCP) congestion control algorithm, using Closed-Loop Control theory to keep the stable and constant transmission rate. AppTCP can swiftly reach the required transmission rate by increasing the congestion control window, and keep the transmission rate and allows the other TCP flows to share the remaining bandwidth. We further conduct extensive experiments in both fast long distance network test-bed and actual national networks (i.e., from Beijing to Shanghai in China) and international networks (i.e., from Hongkong in China to Chicago in USA) to evaluate and verify the performance and effectiveness of AppTCP. The results show that the AppTCP can effectively utilize the link capacity and maintain the constant rate during the data transmission, and its performance significantly outperforms that of the existing TCP variants.

IDTCP: An effective approach to mitigating the TCP incast problem in data center networks

Recently, TCP incast problem in data center networks has attracted a wide range of industrial and academic attention. Lots of attempts have been made to address this problem through experiments and simulations. This paper analyzes the TCP incast problem in data centers by focusing on the relationships between the TCP throughput and the congestion control window size of TCP. The root cause of the TCP incast problem is explored and the essence of the current methods to mitigate the TCP incast is well explained. The rationality of our analysis is verified by simulations. The analysis as well as the simulation results provides significant implications to the TCP incast problem. Based on these implications, an effective approach named IDTCP (Incast Decrease TCP) is proposed to mitigate the TCP incast problem. Analysis and simulation results verify that our approach effectively mitigates the TCP incast problem and noticeably improves the TCP throughput.

Estimation of Fading Statistics of Nakagami Channel with Weibull Distributed Tolerable Outage Time

Characterization of a mobile radio channel plays an important role in designing a reliable wireless communication system. Such channels are analyzed by two state model, namely satisfactory and outage state. This paper presents the analysis to estimate fading parameters of wireless channel with omission of certain outage durations which are considered as “Tolerance time”. Minimum outage duration which can be tolerated by a wireless fading channel to achieve desired packet error rate is defined as tolerance time. Normally a system with tolerable minimum outage time is analyzed based on Fade Duration Distribution (FDD) function over Rayleigh channel. In this paper Weibull function is used as FDD for varying tolerance time. The approach is simple and in general applicable from Rayleigh to Nakagami channels. The analysis is extended to study the effect of Tolerance time on channel fading statistics such as Average Fade Duration (AFD) and frequency of outage. Further the effects of various fade margin and Doppler spread on fading parameters are also investigated. The analysis can also be used in case of timeout expiration, connection resetting and congestion window control.

Quality of Service Control for WLAN-based Converged Personal Network Service

This paper proposes a framework for quality of service (QoS) control in WLAN-based converged personal network service (CPNS). First, we show that the CPNS devices in WLANs occupy the shared wireless channel in an unfair manner; and thus, QoS is degraded. The reasons of such problem are analyzed from two viewpoints of (i) channel access mechanism according to carrier sensing multiple access protocol of WLAN and (ii) TCP congestion control mechanism in response to packet loss. To improve QoS and assure fair channel sharing, we propose an integrated QoS control framework consisting of admission control and rate control. Based on the available capacity, the admission control determines whether or not a specific QoS service can be admitted. The rate control is implemented using congestion window control or token bucket algorithm. The proposed mechanism differentiates QoS service from best-effort (BE) service such that the QoS service is preferentially served to satisfy its QoS requirements and the BE service is served to share the remaining resource in a fair manner. The extensive simulation results confirm that the proposed scheme assures QoS and fair channel sharing for WLAN-based CPNS.

Appropriate SACK Handling for Temporary Disconnections in a Wireless Multi-Homed Environment

In this letter, we describe inappropriate SACK (Selective Acknowledgement) handling in SCTP multi-homed environment, and propose a simple modification. The main idea of the modification is that a sender does not increase the congestion control window size of a primary path when availability of the path is ambiguous. Through simulation, we show that the performance is much improved with this simple modification compared to standard SCTP.

Queuing dynamics and single-link stability of delay-based window congestion control

Accurate modeling of queueing dynamics is important in the design and analysis of Internet congestion control. However, as demonstrated in this paper, existing window-based queueing models [26,30] are often not capable of precisely capturing the transient behavior (i.e., self-clocking and burstiness) of TCP-like protocols and their resulting analysis may be inaccurate in practice. As one example, we show that stability conditions of FAST TCP based on traditional queuing models [17] that do not considering transient dynamics of the queues are inconsistent with ns2 simulations. We explain the origin of this problem and overcome it by developing a novel approach called Self-clocking Queuing Model (SQM) that accurately describes both the steady-state and transient queuing behavior of window-based control systems. Using SQM and explicitly incorporating control interval hi in the queuing model and derive a sufficient condition for its local stability under homogeneous delay, which strengthens prior results [29,30] obtained using traditional queuing models.

A cross-layer congestion and contention window control scheme for TCP performance improvement in wireless LANs

Neither the current TCP protocol nor the standard backoff algorithm of IEEE 802.11 protocol is able to distinguish corruption loss from congestion or collision loss. Hence, high transmission errors and a varying latency inherent in wireless channel would have a seriously adverse effect on the performance of TCP. In this paper, we propose a novel and pragmatic cross-layer approach with joint congestion and contention window control scheme to improve the performance of TCP in IEEE 802.11 wireless environments. In addition to theoretical analysis, simulations are conducted to evaluate the proposed scheme. As it turns out, our design indeed provides a more efficient solution for frequent transmission loss and enables TCP to distinguish between congestion loses and transmission errors, thus to take proper remedial actions.

LIAD: Adaptive bandwidth prediction based Logarithmic Increase Adaptive Decrease for TCP congestion control in heterogeneous wireless networks

For accessing plentiful resources in the Internet through wireless mobile hosts, diverse wireless network standards and technologies have been developed and progressed significantly. The most successful examples include IEEE 802.11 WiFi for wireless networks and 3G/HSDPA/HSUPA for cellular communications . All IP-based applications are the primary motivations to make these networks successful. In TCP/IP transmissions, the TCP congestion control operates well in the wired network, but it is difficult to determine an accurate congestion window in a heterogeneous wireless network that consists of the wired Internet and various types of wireless networks. The primary reason is that TCP connections are impacted by not only networks congestion but also error wireless links. This paper thus proposes a novel adaptive window congestion control (namely Logarithmic Increase Adaptive Decrease, LIAD) for TCP connections in heterogeneous wireless networks. The proposed RTT-based LIAD has the capability to increase throughput while achieving competitive fairness among connections with the same TCP congestion mechanism and supporting friendliness among connections with different TCP congestion control mechanisms. In the Congestion Avoidance (CA) phase, an optimal shrink factor is first proposed for Adaptive Decreasing cwnd rather than a static decreasing mechanism used by most approaches. Second, we adopt a Logarithmic Increase algorithm to increase cwnd while receiving each ACK after causing three duplicate ACKs. The analyses of congestion window and throughput under different packet loss rate are analyzed. Furthermore, the state transition diagram of LIAD is detailed. Numerical results demonstrate that the proposed LIAD outperforms other approaches in goodput, fairness, and friendliness under diverse heterogeneous wireless topologies. Especially, in the case of 10% packet loss rate in wireless links, the proposed approach increases goodput up to 156% and 1136% as compared with LogWestwood+ and NewReno, respectively.

Quick Vegas: Improving Performance of TCP Vegas for High Bandwidth-Delay Product Networks

An important issue in designing a TCP congestion control algorithm is that it should allow the protocol to quickly adjust the end-to-end communication rate to the bandwidth on the bottleneck link. However, the TCP congestion control may function poorly in high bandwidth-delay product networks because of its slow response with large congestion windows. In this paper, we propose an enhanced version of TCP Vegas called Quick Vegas, in which we present an efficient congestion window control algorithm for a TCP source. Our algorithm improves the slow-start and congestion avoidance techniques of original Vegas. Simulation results show that Quick Vegas significantly improves the performance of connections as well as remaining fair when the bandwidth-delay product increases.

TCP-Ho: A Congestion Control Algorithm with Design and Performance Evaluation

A critical design issue of Transmission Control Protocol (TCP) is its congestion control that allows the protocol to adjust the end-to-end communication rate based on the detection of packet loss. However, TCP congestion control may function poorly during its slow start and congestion avoidance phases. This is because TCP sends bursts of packets with the fast window increase and the ACK-clock based transmission in slow start, and respond slowly with large congestion windows especially in high bandwidth-delay product (BDP) networks during congestion avoidance. In this article, we propose an improved version of TCP, TCP-Ho, that uses an efficient congestion window control algorithm for a TCP source. According to the estimated available bandwidth and measured round-trip times (RTTs), the proposed algorithm adjusts the congestion window size with a rate between exponential growth and linear growth intelligently. Our extensive simulation results show that TCP-Ho significantly improves the performance of connections as well as remaining fair and stable when the BDP increases. Furthermore, it is feasible to implement because only sending part needs to be modified.

TCP Westwood with adaptive bandwidth estimation to improve efficiency/friendliness tradeoffs

In this paper, we propose an extension of Transmission Control Protocol (TCP) Westwood allowing the management of the Efficiency/Friendliness-to-NewReno tradeoffs. We show that the extended TCP Westwood is able to achieve higher total link utilization, yet at the same time maintain friendliness. TCP Westwood (for short, TCPW) implements a novel window congestion control algorithm based on eligible rate estimation (RE). The performance of TCPW has been promising, exceeding that of TCP NewReno in ‘large leaky pipes’; i.e. network paths with high bandwidth-delay product and non-negligible random error rate. Consider the situation where TCPW and TCP NewReno connections coexist and share common bottlenecks. Friendliness in this shared environment is paramount. Under certain conditions TCP NewReno may experience some performance degradation since TCPW ‘learns’ more about connection performance and thus can take better advantage of available bandwidth. To manage the efficiency/friendliness tradeoffs, we propose to combine the original TCPW Bandwidth Estimation (BE) strategy with a new RE strategy. One finds that BE provides significantly higher utilization, but may, under certain conditions, overestimates a connection fair share. RE, on the other hand, tends to be closer to the achieved rate of a connection, but it may underestimate the connection fair share. The question is: which estimate—RE or BE—yields better throughput/friendliness tradeoffs? Our studies show that RE works best when packet loss is mostly due to congestion. If, on the other hand, packet loss is mostly due to link errors, BE gives better performance. To achieve the ‘best of all worlds’, we introduce a method we call Combined Rate and Bandwidth estimation (CRB.) A connection first infers the predominant cause of packet loss (buffer congestion or random error) and then uses the more appropriate estimation method. Simulation shows that the adaptive CRB provides a very effective compromise between efficiency and friendliness.