Loss-based Congestion Control Algorithms Research Articles

Evaluation of Modern Internet Transport Protocols over GEO Satellite Links

New versions of HTTP protocols have been developed to overcome many of the limitations of the original HTTP/1.1 protocol and its underlying transport mechanism over TCP. In this paper, we investigated the performance of modern Internet protocols such as HTTP/2 over TCP and HTTP/3 over QUIC in high-latency satellite links. The goal was to uncover the interaction of the new features of HTTP such as parallel streams and optimized security handshake with modern congestion control algorithms such as CUBIC and BBR over high-latency links. An experimental satellite network emulation testbed was developed for the evaluation. The study analyzed several user-level web performance metrics such as average page load time, First Contentful Paint and Largest Contentful Paint. The results indicate an overhead problem with HTTP/3 that becomes more significant when using a loss-based congestion control algorithm such as CUBIC which is widely used on the Internet. Also, the results highlight the significance of the web page structure and how objects are distributed in it. Among the various Internet protocols evaluated, the results show that HTTP/3 over QUIC will perform better by an average of 35% than HTTP/2 over TCP in satellites links specifically with a more aggressive congestion algorithm such as BBR. This can be attributed to the non-blocking stream multiplexing feature of QUIC and the reduced TLS handshake of HTTP/3.

Improving the TCP Newreno Congestion Avoidance Algorithm on 5G Networks

Enhancing Transmission Control Protocol (TCP) performance is one of the key solutions for improving the performance of modern wireless communication networks. It is a highly dependable protocol for communication between network hosts based on an internet protocol (IP). It uses packet sequence numbering and acknowledgment (ACK) packets to ensure that data is recoverable in the event of problems like data loss, and corruption. Loss-based Congestion Control (CC) algorithms overreact and underperform in the presence of rapid channel oscillations, resulting in buffer bloat and significant delays. The goal of this paper is to develop an efficient congestion control mechanism for the new TCP agent Newreno over the fifth generation (5G) network, as well as to improve the increment and decrement strategy for adjusting the congestion window (cwnd) during the congestion avoidance phase, It also fast adapts to the current network requirements and adjusts the transmission rate accordingly. TCP enhancements can improve performance under dynamic traffic loads and over long product channels with high bandwidth. As a result, when such a TCP congestion control mechanism is improved, the network’s throughput increases, and low packet losses, and delay are reduced.

Effective IoT Congestion Control Algorithm

The Internet of Things (IoT) connects devices via the Internet. Network congestion is one of the key problems that has been identified by researchers in the IoT field. When there is a huge number of IoT devices connected to the internet, this creates network congestion. Transfer control protocol is a transport layer protocol that provides a reliable end-to-end connection between two devices. Many Congestion Control Algorithms have been proposed to solve network congestion. However, there is no perfect solution to this problem. This paper proposes an effective loss-based Congestion Control Algorithm to effectively adapt the congestion window in the IoT environment. It uses simple experiment scenarios to test the algorithm for wired and wireless channels and observes important performance metrics: link utilization, inter-protocol fairness, intra-protocol fairness and throughput. The results are impressive, and the proposed algorithm is shown to outperform other standard algorithms.

Effects on random early detection of the packet drop probability function with an adjustable nonlinearity

This paper proposed a packet drop probability function with an adjustable nonlinearity parameter in random early detection (RED) for active queue management of a router to control network congestion. We investigated the effect of nonlinearity on the average queue size, average throughput, average retransmission rate, average round-trip time, and fairness index for two widely used loss-based congestion control algorithms: Reno and CUBIC. Simulations were performed with Tail-Drop and the original RED to clarify the effect of nonlinearity under different traffic loads. The results showed that the RED with a nonlinear function did not aggravate the network performance statistics because achieved high throughput while maintaining a low-queuing delay, such as the original RED with a linear function under the extremely heavy traffic condition. Under the light and the heavy traffic conditions, increasing the bending degree of the nonlinear function accomplished high throughput by preventing excessive discarding of packets.

Optimizing Data Transport Efficiency in Datacenters through Traffic Shaping of BBR Congestion Control

Compared to commonly used loss-based congestion control algorithms predominantly used in Transmission Control Protocol (TCP) implementations, congestion-based congestion control called BBR has shown much better performance in resource-abundant modern communication links. However, for a high influx of TCP sessions on the bottleneck switch, clusters in High-Performance Compute (HPC) nodes and data centers face resource constraints because of the immense workload during orchestration and relocation of workflows across the resource pool. This article discusses how to resolve this problem, commonly known as TCP incast, through efficient queue management of the bottleneck link and adding a shaper function in the standard BBR algorithm. We analyzed TCP incast issue for two efficient versions of congestion control i.e., BBR and CUBIC (named after the cubic function used instead of linear function), in a highly overloaded convergent switch of the cluster. It is noticeable that the queuing delay and buffer build-up are two essential parameters in causing TCP Incast. Hence, we used the M/G/1/B queuing model when multiple TCP sessions generate the network traffic and different buffer build-up scenarios are analyzed in the bottleneck node of HPC clusters. Based on the findings of our queuing analysis, we propose an incast recovery BBR algorithm that introduces additional controls like Incast shaping to deal with queue build-up during TCP incast. The effects of these modifications in BBR implementation are studied in terms of performance parameters like flow completion time, throughput, RTT variations, and fairness to other competing flows are significant compared with standard BBR and CUBIC implementations.

BBRv2+: Towards balancing aggressiveness and fairness with delay-based bandwidth probing

BBRv2, proposed by Google, aims at addressing BBR’s shortcomings of unfairness against loss-based congestion control algorithms (CCAs) and excessive retransmissions in shallow-buffered networks. In this paper, we first comprehensively study BBRv2’s performance under various network conditions and show that BBRv2 mitigates the shortcomings of BBR. Nevertheless, BBRv2’s benefits come with several costs, including slow responsiveness to bandwidth dynamics and low resilience to random losses. We then propose BBRv2+ to address BBRv2’s performance issues without sacrificing its advantages over BBR. To this end, BBRv2+ uses delay information to cautiously guide the aggressiveness of its bandwidth probing. In doing so, it achieves fast responsiveness to bandwidth dynamics and fairness against loss-based CCAs at the same time. BBRv2+ also integrates mechanisms for improved resilience to random losses and network jitter. Extensive experiments demonstrate the effectiveness of BBRv2+. Specifically, it achieves 25% higher throughput and comparable queuing delay in comparison with BBRv2 in high-mobility network scenarios.

Understanding of BBRv2: Evaluation and Comparison With BBRv1 Congestion Control Algorithm

Google proposed a bottleneck bandwidth round-trip propagation time (BBR) for TCP to replace the loss-based congestion control algorithms, such as Reno and CUBIC. Unlike the loss-based algorithms, BBR models a network path from source to destination and dynamically controls the sending rate using control parameters, such as pacing rate, congestion window, and quantum to achieve high throughput and low latency. However, many studies have reported performance issues in BBR operation, such as excessive packet loss in shallow buffers, the unfairness among different RTT flows, the unfairness with loss-based algorithms, and so on. Google is developing a new version of BBR, BBRv2, to resolve these performance issues. In this study, we evaluate and compare two versions of BBR on a Mininet emulator and a physical testbed, focusing on whether the BBRv2 alpha can alleviate the performance issues of BBRv1 and whether other novel issues will arise in BBRv2. The experiment results show that BBRv2 improves the unfairness and aggressiveness in small buffer less than 1 BDP. Moreover, multiple BBRv2 flows not only show better fairness in bandwidth sharing, but also reduce the amount of packet retransmissions. However, we observed that the challenging issues such as RTT unfairness, coexistence with loss-based algorithms, and synchronization between BBRv2 flows still exist. This study explores BBRv2’s current behavior in various network scenarios and compares the performance of BBRv2 with the BBRv1 congestion control algorithm.

An emulation-based evaluation of TCP BBRv2 Alpha for wired broadband

Google published the first release of the Bottleneck Bandwidth and Round-trip Time (BBR) congestion control algorithm in 2016. Since then, BBR has gained a widespread attention due to its ability to operate efficiently in the presence of packet loss and in scenarios where routers are equipped with small buffers. These characteristics were not attainable with traditional loss-based congestion control algorithms such as CUBIC and Reno. BBRv2 is a recent congestion control algorithm proposed as an improvement to its predecessor, BBRv1. Preliminary work suggests that BBRv2 maintains the high throughput and the bounded queueing delay properties of BBRv1. However, the literature has been missing an evaluation of BBRv2 under different network conditions.This paper presents an experimental evaluation of BBRv2 Alpha (v2alpha-2019-07-28) on Mininet, considering alternative active queue management (AQM) algorithms, routers with different buffer sizes, variable packet loss rates and round-trip times (RTTs), and small and large numbers of TCP flows. Emulation results show that BBRv2 tolerates much higher random packet loss rates than loss-based algorithms but slightly lower than BBRv1. The results also confirm that BBRv2 has better coexistence with loss-based algorithms and lower retransmission rates than BBRv1, and that it produces low queuing delay even with large buffers. When a Tail Drop policy is used with large buffers, an unfair bandwidth allocation is observed among BBRv2 and CUBIC flows. Such unfairness can be reduced by using advanced AQM schemes such as FQ-CoDel and CAKE. Regarding fairness among BBRv2 flows, results show that using small buffers produces better fairness, without compromising high throughput and link utilization. This observation applies to BBRv1 flows as well, which suggests that rate-based model-based algorithms work better with small buffers. BBRv2 also enhances the coexistence of flows with different RTTs, mitigating the RTT unfairness problem noted in BBRv1. Lastly, the paper presents the advantages of using TCP pacing with a loss-based algorithm, when the rate is manually configured a priori. Future algorithms could set the pacing rate using explicit feedback generated by modern programmable switches.

BBR-CWS: Improving the Inter-Protocol Fairness of BBR

TCP congestion control adjusts the sending rate in order to protect Internet from the continuous traffic and ensure fair coexistence among multiple flows. Especially, loss-based congestion control algorithms were mainly used, which worked relatively well for past Internet with low bandwidth and small bottleneck buffer size. However, the modern Internet uses considerably more sophisticated network equipment and advanced transmission technologies, and loss-based congestion control can cause performance degradation due to excessive queueing delay and packet loss. Therefore, Google introduced a new congestion control in 2016, Bottleneck Bandwidth Round-trip propagation time (BBR). In contrast with traditional congestion control, BBR tries to operate at the Kleinrock’s optimal operating point, where delivery rate is maximized and latency is minimized. However, when BBR and loss-based congestion control algorithms coexist on the same bottleneck link, most of bottleneck bandwidth is occupied by flows that use a particular algorithm, and excessive packet retransmission can occur. Therefore, this paper proposes a BBR congestion window scaling (BBR-CWS) scheme to improve BBR’s inter-protocol fairness with a loss-based congestion control algorithm. Through Mininet experiment results, we confirmed that fairness between BBR-CWS and CUBIC improved up to 73% and has the value of 0.9 or higher in most bottleneck buffer environments. Moreover, the number of packet retransmissions was reduced by up to 96%, compared to the original BBR.

BBR-ACD: BBR with Advanced Congestion Detection

With the aim of improved throughput with reduced delay, Google proposed the bottleneck bandwidth and round-trip time (BBR) congestion control algorithm in 2016. Contrasting with the traditional loss-based congestion control algorithms, it operates without bottleneck queue formation and packet losses. However, we find unexpected behaviour in BBR during testbed experiments and network simulator 3 (NS-3) simulations. We observe huge packet losses, retransmissions, and large queue formation in the bottleneck in a congested network scenario. We believe this is because of BBR’s nature of sending extra data during the bandwidth probing without considering the network conditions, and the lack of a proper recovery mechanism. In a congested network, the sent extra data creates a large queue in the bottleneck, which is sustained due to insufficient drain time. BBR lacks a proper mechanism to detect such large bottleneck queues, cannot comply with the critical congestion situation properly, and results in excessive retransmission problems. Based on these observations, we propose a derivative of BBR, called “BBR with advanced congestion detection (BBR-ACD)”, that reduces the excessive retransmissions without losing the merits. We propose a novel method to determine an actual congestion situation by considering the packet loss and delay-gradient of round-trip time, and implement a proper recovery mechanism to handle such a congestion situation. Through extensive test and NS-3 simulations, we confirmed that the proposed BBR-ACD could reduce the retransmissions by about 50% while improving the total goodput of the network.

Delay-Aware BBR Congestion Control Algorithm for RTT Fairness Improvement

In late 2016, Google proposed the Bottleneck Bandwidth and Round-trip propagation time (BBR) congestion control algorithm to achieve high bandwidth and low latency for Internet traffic. Unlike loss-based congestion control algorithms, BBR works without filling the bottleneck buffer. Consequently, BBR can reduce packet loss and minimize end-to-end packet delay, which has attracted the attention of many researchers in recent years. However, some studies have reported the creation of persistent queues that cause unintended problems, resulting in a serious fairness issue between TCP BBR flows with different round-trip times (RTTs). Although existing congestion control algorithms also exhibit fairness issue between different RTT flows, BBR has a more serious problem in that the imbalance is considerable even with small RTT difference between the two flows, and the long RTT flow uses most of the bandwidth. The preponderance of long RTT flows is a serious problem because a particular user may cause imbalance by maliciously increasing the delay. Therefore, we propose a Delay-Aware BBR (DA-BBR) congestion control algorithm to mitigate the RTT fairness issue between BBR flows. In a network emulation experiment using the Mininet, the DA-BBR increased the fairness index by 1.6 times that of the original BBR, and the retransmission was greatly reduced. DA-BBR flow with short RTT demonstrated fair throughput even in competition with DA-BBR flows where RTT is five times higher.

Modeling the Throughput of the Linux-Based Agile-SD Transmission Control Protocol

Agile-SD is one of the latest versions of loss-based congestion control algorithm (CCA), which has been proposed to improve the total performance of transmission control protocol (TCP) over high-speed and short-distance networks. It has introduced a new mechanism, called agility factor mechanism, which shortens the epoch time to reduce the sensitivity to packet losses and in turn to increase the average throughput. Agile-SD has only been tested via simulation; however, it has not been mathematically proven or evaluated. The contribution of this paper is twofold. First, a new mathematical model for the throughput of NewReno and Agile-SD is proposed. This model is designed using the well-known Markov chains to validate the correctness of Agile-SD and to show the impact of buffer size, multiplicative decrease factor, and maximum limit of agility factor ({\lambda}max ) on the total performance. Second, an automated algorithm configuration and parameter tuning (AACPT) technique is employed to optimize and automate the configuration of {\lambda}max . Furthermore, the numerical results for both NewReno and Agile-SD are compared with the simulation results, in which the validity of the proposed model is confirmed. Moreover, the output of the AACPT is exploited to formulate a new equation, which calculates the optimal {\lambda}max from a given \b{eta} in order to conserve the standard interface of the TCP. This equation increases the scalability of Agile-SD and improves its total performance.