TCP Sender Research Articles

TCP 송수신자간의 큐사용률 추정을 이용한 송신자 기반의 패킷손실 구별기법

멀티홉 무선 네트워크에서 TCP가 동작하는 경우, 유선 네트워크와 무선 네트워크의 서로 다른 특성으로 인하여 TCP의 심각한 성능저하가 초래된다. 이것은 TCP가 무선오류로 인해 발생되는 패킷손실을 혼잡으로 인해 발생한 패킷손실로 간주하여 데이터 전송률을 불필요하게 감소시키기 때문이다. 이러한 성능저하를 피하기 위해서 혼잡손실과 무선손실을 구별하는 많은 기법들이 연구되어 왔으나, 이들 기법들은 무선손실에 대한 탐지정확도가 기대만큼 높지 않거나, 무선손실에 대한 탐지정확도가 높으면 혼잡손실에 대한 정확도가 낮아지는 경향을 보인다. 본 논문은 혼잡손실에 대한 탐지정확도의 희생을 최소화하면서, 무선손실에 대한 탐지정확도를 높이는 송신자 기반의 패킷손실 구별기법을 제안한다. 본 기법은 네트워크 혼잡과 상호 관련성이 높은TCP 송 수신자간의 큐 사용률을 추정하고, 추정된 큐 사용률과 특정 임계값을 비교하여 혼잡손실과 무선손실을 구별한다. 네트워크 시뮬레이터인 QualNet을 이용한 실험에서는 기존 기법과 제시된 기법간의 혼잡손실에 대한 탐지정확도와 무선손실에 대한 탐지정확도를 구분하여 비교평가하고, 홉 수 증가에 따른 성능향상을 비교평가 한다. 실험 결과는 멀티홉 무선 네트워크상에서 본 기법이 가장 높은 탐지정확도를 가질 뿐만 아니라 TCP의 성능을 가장 높게 향상시킴을 보인다. When TCP operates in multi-hop wireless networks, it suffers from severe performance degradation due to the different characteristics of wireless networks and wired networks. This is because TCP reacts to wireless packet losses by unnecessarily decreasing its sending rate assuming the losses as congestion losses. Although several loss differentiation algorithms (LDAs) have been proposed to avoid such performance degradation, their detection accuracies are not high as much as we expect. In addition the schemes have a tendency to sacrifice the detection accuracy of congestion losses while they improve the detection accuracy of wireless losses. In this paper, we suggest a new sender-based loss differentiation scheme which enhances the detection accuracy of wireless losses while minimizing the sacrifice of the detection accuracy of congestion losses. Our scheme estimates the rate of queue usage which is highly correlated with the congestion in the network path between a TCP sender and a receiver, and it distinguishes congestion losses from wireless losses by comparing the estimated queue usage with a certain threshold. In the extensive experiments based on a network simulator, QualNet, we measure and compare each detection accuracy of wireless losses and congestion losses, and evaluate the performance enhancement in each scheme. The results show that our scheme has the highest accuracy among the LDAs and it improves the most highly TCP performance in multi-hop wireless networks.

On the search of efficient AQM for large delay networks

The main idea of all Active Queue Management algorithms, is to notify the TCP sender about incoming congestion by dropping packets, to prevent from the buffer overflow, and its negative consequences. However, most AQM algorithms proposed so far, neglect the impact of the high speed and long delay links. As a result, the algorithms' efficiency, in terms of throughput and/or queue stability, is usually significantly decreased. The contribution of this paper is twofold. First of all, the performance of the well known AQM algorithms in high speed and long delay scenarios is evaluated and compared. Secondly, a new AQM algorithm is proposed, to improve the throughput in the large delay scenarios and to exclude the usage of random number generator.

Multi-layer loss recovery in TCP over optical burst-switched networks

It is well-known that the bufferless nature of optical burst-switching (OBS) networks cause random burst loss even at low traffic loads. When TCP is used over OBS, these random losses make the TCP sender decrease its congestion window even though the network may not be congested. This results in significant TCP throughput degradation. In this paper, we propose a multi-layer loss-recovery approach with automatic retransmission request (ARQ) and Snoop for OBS networks given that TCP is used at the transport layer. We evaluate the performance of Snoop and ARQ at the lower layer over a hybrid IP-OBS network. Based on the simulation results, the proposed multi-layer hybrid ARQ + Snoop approach outperforms all other approaches even at high loss probability. We developed an analytical model for end-to-end TCP throughput and verified the model with simulation results.

Analysis of RTO Caused by Retransmission Loss to Combat Channel Noise

A Retransmission Time Out (RTO) is inevitable, when the retransmission of a packet fails to reach the receiver. An RTO compels TCP to reduce packet flow drastically. However, in case of an RTO resulting from retransmission failure caused by the channel noise, reduction in the flow is inappropriate. The problem is compounded when a TCP sender is forbidden to continue transmission till the occurrence of the timeout. In this paper, we investigate the impact of such RTOs with the help of an empirical mathematical analysis. The analysis presented in the paper calculates the idle period of the sender in terms of number of RTTs, which depends on the value of congestion window before the timeout. The mathematical analysis is supported by the results of simulation based experiments and the evaluation of a scheme that improves TCP performance in case of avoidable timeouts caused by the loss of retransmission on an erroneous wireless link.

Performance Analysis of TCP with Delayed Acknowledgments in Multi-hop Ad-hoc Networks

The acknowledgment strategy has great potential to increase TCP throughput when it runs over 802.11 MAC protocol. In particular, TCP acknowledgments (ACK) carry out an extensive number of medium accesses as they compete in the same route as data packets for media. In this paper, we first propose a dynamic TCP-MAC interaction strategy which tries to reduce the number of induced ACKs by monitoring the channel condition. To this end, the total collision probability collected along the path from sender to receiver in MAC layer has been used to properly set the number of delayed ACKs (DA) in TCP. Based on the estimated collision probability, TCP sender dynamically adjusts itself to the channel condition by delaying less ACKs in high traffic conditions and more ACKs in low traffic conditions. The simulation results show a throughput improvement up to 15% over the existing method called Dynamic Adaptive Acknowledgment (TCP-DAA) and much more over the regular TCP in different scenarios dealing with a dynamic loss rate. In addition, we show that our proposed strategy does not always benefit from a fixed delay policy along with a fixed congestion window size. In fact, the optimal number of delayed ACKs is based on the path length of a TCP connection and a large delay window may solely improve TCP throughput in short ranges with less number of flows. However, in a longer path congestion window limit provides more throughput gain.

Measurement and performance issues of transport protocols over 10Gbps high-speed optical networks

With the integration of IP and optical technology, a high-speed optical network (of the order of 10Gbps) has emerged to support international research cooperation such as massive scientific data transfer and next generation Internet related research. Therefore, it is critical to explore the issues of measurement and evaluation on the performance of transport protocols over 10 Gbps high-speed optical networks. To the best of our knowledge, this is the first work that presents a measurement study on a variety of networking environments. The objectives of this paper are as follows: (i) determine the suitability of TCP parameters such as Jumbo Frame size, buffer sizes of a TCP sender and a receiver; (ii) evaluate TCP performance measurement tools and emulation tools over 10 Gbps high-speed optical networks; and (iii) compare performance of TCP variants with different metrics, such as throughput and fairness, by varying delays and randomized losses controlled with software emulators. The result shows that selection of emulation and performance measurement tools matters for the accurate measurement of TCP performance. The performance of TCP variants is highly impacted by the Linux TCP/IP stack tuning. Finally we present that overall and detailed performance, such as throughput and fairness, of each TCP variant is dependent on different network environments, such as packet loss rate and propagation delay.

Cross-Layer Explicit Link Status Notification to Improve TCP Performance in Wireless Networks

To alleviate the performance degradation of conventional TCP in wireless networks, many schemes have been proposed so far. One category of such schemes is the Explicit Loss Notification (ELN) scheme in which TCP senders are notified of wireless losses so as to avoid congestion control against those losses. Thus the key design factor of the ELN scheme is how to detect wireless losses accurately and rapidly. This paper proposes a new ELN scheme, in which wireless losses are detected by monitoring the operation of the wireless link layer. By exploiting such cross-layer design, the proposed scheme can detect wireless losses without additional transmission over the wireless link and thus achieves accurate detection with minimum delay. The proposed scheme additionally sends new information, that is, Explicit Retransmission Start Notification, in order to prevent spurious timeouts of the TCP senders. Furthermore, in order to handle packet reordering and avoid successive shrinking of a congestion window due to multiple packet drops, a new TCP modification is proposed. Through intensive simulations, it is demonstrated that the proposed scheme outperforms the other ELN schemes, and yields the throughput performance of more than 400% of TCP-Reno and 150% of Snoop in the considered environments.

Basestation flow control for wired to wireless networks

With the exponential growth of the internet, wireless networks such as satellite networks are becoming increasingly popular. The characteristics of satellite networks such as long latency, large delay-bandwidth product, high bit error rate over satellite links and variable round trip time, severely degrade TCP/IP performance. At the conjunction of the satellite link and the fixed link, the basestation, the difference in capacity between the satellite link and the fixed link causes the basestation to experience congestion losses that adversely impact TCP performance. We propose a technique that substantially reduces the congestion at the base station and enforces fairness among the TCP connections that are sharing the satellite link. The technique does not require any change in the TCP sender or the receiver. The stability of our algorithm is analytically proven and its performance is evaluated using ns-2 simulations. Preliminary results yield almost a null congestion loss rate, a 60% decrease in average queue length, and more than 30% increase in the throughput. Fairness is well enforced.

TCP transmission rate control mechanism based on channel utilization and contention ratio in AD hoc networks

In ad hoc networks, both contention and congestion can severely affect the performance of TCP. In our work, we first show that the over-injection of conventional TCP window mechanism results in severe contentions, and medium contentions cause network congestion. Furthermore, introducing two metrics, channel utilization (CU) and contention ratio (CR), we characterize the network status. Then, based on these two metrics, we propose a new TCP transmission rate control mechanism based on Channel utilization and Contention ratio (TCPCC). In this mechanism, each node collects the information about the network busy status and determines the CU and CR accordingly. The CU and CR values fed back through ACK are ultimately determined by the bottleneck node along the flow. The TCP sender controls its transmission rate based on the feedback information. Simulation results show that the proposed TCPCC mechanism significantly outperforms the conventional TCP mechanism and the TCP contention control mechanism in terms of throughput and end-to-end delay.

A Novel Congestion Detection Scheme in TCP Over OBS Networks

This paper introduces a novel congestion detection scheme for high-bandwidth TCP flows over optical burst switching (OBS) networks, called statistical additive increase multiplicative decrease (SAIMD). SAIMD maintains and analyzes a number of previous round-trip time (RTTs) at the TCP senders in order to identify the confidence with which a packet loss event is due to network congestion. The confidence is derived by positioning short-term RTT in the spectrum of long-term historical RTTs. The derived confidence corresponding to the packet loss is then taken in the developed policy for TCP congestion window adjustment. We will show through extensive simulation that the proposed scheme can effectively solve the false congestion detection problem and significantly outperform the conventional TCP counterparts without losing fairness. The advantages gained in our scheme are at the expense of introducing more overhead in the SAIMD TCP senders. Based on the proposed congestion control algorithm, a throughput model is formulated, and is further verified by simulation results.

Momentary Recovery Algorithm: A New Look at the Traditional Problem of TCP

Traditional TCP has a good congestion control strategy that adapts its sending rate in accordance with network congestion. In addition, a fast recovery algorithm can help TCP achieve better throughput by responding to temporary network congestion well. However, if multiple packet losses occur, the time to enter congestion avoidance phase would be delayed due to the long recovery time. Moreover, during the recovery phase, TCP freezes congestion window size until all lost packets are recovered, and this can make recovery time much longer resulting in performance degradation. To mitigate such recovery overhead, we propose Momentary recovery algorithm that recovers packet loss without an extra recovery phase. As other TCP and variants, our algorithm also halves the congestion window size when packet drop is detected, but it performs congestion avoidance phase immediately as if loss recovery is completed. For lost packets, TCP sender transmits them along with normal packets as long as congestion window permits rather than performs fast retransmission. In this manner, we can eliminate recovery overhead efficiently and reach steady state momentarily after network congestion. Finally, we provide a simulation based study on TCP recovery behaviors and confirm that our Momentary recovery algorithm always shows better performance compared with NewReno, SACK, and FACK.

On remote exploitation of TCP sender for low-rate flooding denial-of-service attack

This letter shows a potentially harmful scenario named Induced-shrew attack in which a malicious TCP receiver remotely controls the transmission rate and pattern of a TCP sender to exploit it as a flood source for launching low-rate denial-of-service (DoS) attacks. Through simulation, proof-of concept implementation and experimentation in testbed and realworld Internet paths, we demonstrate that standard implementation of TCP senders can be exploited as flood sources for low-rate DoS attacks without compromising them. We describe the nature of the underlying vulnerability and discuss possible countermeasures against the induced-shrew.

TCP throughput enhancement in wired-cum-wireless network

The key idea proposed in this paper is to determine the optimal congestion window for a TCP sender in a particular network scenario (that corresponds to the fair share of that connection) and keep this congestion window a constant to a point where the fair share in the network has changed considerably from the instance of the calculation of the size of the last window. At this point, the TCP congestion window is recalculated according to the nature of new scenario. The proposed mechanism is particularly effective over wireless links, which have an inherently loss-prone nature, as modified TCP’s congestion window being independent of packet losses (be it corruption losses or it congestion losses), keeps transmitting at the same rate at before. We test this scheme under a simulation setup and show that it is performing better than TCP Reno under wireless loss condition and at least at par under wired condition.

A Cross-Layer Approach for Per-Station Fairness in TCP over WLANs

In this paper, we investigate the issue of per-station fairness in TCP over IEEE 802.11-compliant wireless local area networks (WLANs), especially in Wi-Fi hot spot. It is asserted that the hot spot suffers from the unfairness among stations in exploiting the wireless medium. The source of this unfairness is analyzed from two aspects, TCP-induced asymmetry and MAC-induced asymmetry; the former causes TCP congestion control with a cumulative acknowledgment mechanism to prefer the sending stations to receiving stations, while the later exacerbates the unfairness problem in the hot spots. We investigate the interaction between TCP congestion control and MAC contention control, and propose a cross-layer feedback approach to assure per-station fairness and to ensure high channel utilization. In this approach, we introduce the notion of channel access cost to quantify the system-wide traffic load and per-station channel usage. The access cost is estimated at the MAC in an access point and conveyed to the TCP sender. Then, the TCP sender adjusts its sending rate based on the access cost, so as to assure per-station fairness. The simulation results indicate that the proposed approach can provide both per-station fairness and high channel utilization, irrespective of network configurations.

TCP over OBS: Impact of consecutive multiple packet losses and improvements

In TCP over OBS networks, consecutive multiple packet losses are common since an optical burst usually contains a number of consecutive packets from the same TCP sender. In this paper, we first present a new theoretical method to analyze the behavior of Reno when consecutive multiple packet losses occur. Results of the analysis indicate that even a small number of consecutive multiple packet losses can force Reno to timeout. Then we propose B-Reno, a newly designed TCP implementation that can overcome Reno’s inefficiency in dealing with consecutive multiple packet losses over OBS networks and can avoid the shortcomings of New-Reno and SACK. Results of comprehensive simulations indicate that B-Reno over OBS networks can achieve a performance better than Reno and New-Reno, and that it can also achieve a performance similar to that of SACK. Moreover, B-Reno only needs some simple modifications to New-Reno at the sender’s protocol stack, and thus has less difficulty in deployment and less protocol complexity than that of SACK.

Performance Enhancement of TCP in Dynamic Bandwidth Wired and Wireless Networks

In this paper, we propose a scheme that dynamically adjusts the slow start threshold (ssthresh) of TCP. The ssthresh estimation is used to set an appropriate ssthresh. A good ssthresh would improve the transmission performance of TCP. For the congestion avoidance state, we present a mechanism that probes the available bandwidth. We adjust the congestion window size (cwnd) appropriately by observing the round trip time (RTT) and reset the ssthresh after quick retransmission or timeout using the ssthresh estimation. Then the TCP sender can enhance its performance by using the ssthresh estimation and the observed RTT. Our scheme defines what is considered an efficient transmission rate. It achieves better utilization than other TCP versions. Simulation results show that our scheme effectively improves TCP performance. For example, when the average bottleneck bandwidth is close to 30% of the whole network bandwidth, our scheme improves TCP performance by at least 10%.

Improving Reno and New-Reno's performances over OBS networks without SACK

In TCP over optical burst switching (OBS) networks, consecutive multiple packet losses are common since an optical burst usually contains a number of consecutive packets from the same TCP sender. It has been proved that over OBS networks Reno and New-Reno achieve lower throughput performances than that of SACK, which can address the inefficiency of Reno and New-Reno in dealing with consecutive multiple packet losses. However, SACK adopts complex mechanisms not only at the sender's but also at the receiver's protocol stack, and thus has a higher difficulty in deployment. In this paper we propose B-Reno, a new TCP implementation designed for TCP over OBS networks. Using some simple modifications to New-Reno only at the sender's protocol stack, B-Reno can overcome the inefficiencies of Reno and New-Reno in dealing with consecutive multiple packet losses and thus improve their throughputs over OBS networks. Moreover, B-Reno can also achieve performance similar with that of SACK over OBS networks while avoiding SACK's difficulty in deployment due to complex mechanisms at both the sender's and the receiver's protocol stack.

Employing cross-layer assisted TCP algorithms to improve TCP performance with vertical handoffs

In this paper we study the performance of TCP with a vertical handoff between access networks with widely varying link characteristics. TCP being an end-to-end protocol has performance problems as its behaviour depends on the end-to-end path properties which are likely to be affected by a vertical handoff. We propose a set of enhancements to the TCP sender algorithm that leverage on explicit cross-layer information regarding the changes in the access link delay and bandwidth. We carry out a systematic study to identify the problems of regular TCP and compare the performance of the regular TCP with the performance of the enhanced TCP algorithms in various handoff scenarios between access networks having different bandwidth and delay characteristics. Our experiments show that with cross-layer notifications TCP performance can be improved significantly in most vertical handoff scenarios.

A novel TCP with dynamic Burst-Contention Loss notification over OBS networks

In this paper, a novel congestion control scheme with dynamic Burst-Contention Loss notifications in Optical Burst Switching (OBS) networks is proposed. The proposed scheme, called TCP-BCL, aims to handle various OBS bursty conditions that negatively affect TCP throughput performance and fairness. The basic design principle of the scheme is to tune the congestion control parameters @a and @b such that the congestion window sizes in the corresponding TCP senders can be adjusted with an explicit notification from the OBS edge node. The performance impact on TCP in terms of burst dropping due to random contention, which is also known as false congestion detection is considered and investigated. An analytical model is developed and further verified through extensive simulation.

TCP with gateway adaptive pacing for multihop wireless networks with Internet connectivity

This paper introduces an effective congestion control pacing scheme for TCP over multihop wireless networks with Internet connectivity. The pacing scheme is implemented at the wireless TCP sender as well as at the Internet gateway, and reacts according to the direction of TCP flows running across the wireless network and the Internet. Moreover, we analyze the causes for the unfairness of oncoming TCP flows and propose a scheme to throttle aggressive wired-to-wireless TCP flows at the Internet gateway to achieve nearly optimal fairness. The proposed scheme, which we denote as TCP with Gateway Adaptive Pacing (TCP-GAP), does not impose any control traffic overhead for achieving fairness among active TCP flows and can be incrementally deployed since it does not require any modifications of TCP in the wired part of the network. In an extensive set of experiments using ns-2 we show that TCP-GAP is highly responsive to varying traffic conditions, provides nearly optimal fairness in all scenarios and achieves up to 42% more goodput for FTP-like traffic as well as up to 70% more goodput for HTTP-like traffic than TCP NewReno. We also investigate the sensitivity of the considered TCP variants to different bandwidths of the wired and wireless links with respect to both aggregate goodput and fairness.