Congestion Loss Research Articles

Efficient TCP variant with congestion notification for heterogeneous networks

In wireless networks, the packet loss may occur due to high bit error rate, packet corruption and link failures. The existing implementations of TCP interpret the loss occurrence is only due to congestion. This erratic prediction reduces the flow rate of TCP segments and it directly degrades its performance. The TCP variants like TCP New Jersey and TCP NJ+ achieve improvements in goodput over existing TCP NewReno by distinguishing wireless losses from congestion losses. In this paper, we propose an explicit congestion notification (ECN) enabled negative acknowledgement scheme SNACK-NJ, based on TCP NJ+ to further improve the performance of TCP over wireless networks. The simulation results confirm that the proposed scheme outperforms the conventional TCP implementations.

Hospital Quality, Efficiency, and Input Slack Differentials

To use an advance in data envelopment analysis (DEA) called congestion analysis to assess the trade-offs between quality and efficiency in U.S. hospitals. Urban U.S. hospitals in 34 states operating in 2004. Input and output data from 1,377 urban hospitals were taken from the American Hospital Association Annual Survey and the Medicare Cost Reports. Nurse-sensitive measures of quality came from the application of the Patient Safety Indicator (PSI) module of the Agency for Healthcare Research and Quality (AHRQ) Quality Indicator software to State Inpatient Databases (SID) provided by the Healthcare Cost and Utilization Project (HCUP). In the first step of the study, hospitals' relative output-based efficiency was determined in order to obtain a measure of congestion (i.e., the productivity loss due to the occurrence of patient safety events). The outputs were adjusted to account for this productivity loss, and a second DEA was performed to obtain input slack values. Differences in slack values between unadjusted and adjusted outputs were used to measure either relative inefficiency or a need for quality improvement. Overall, the hospitals in our sample could increase the total amount of outputs produced by an average of 26 percent by eliminating inefficiency. About 3 percent of this inefficiency can be attributed to congestion. Analysis of subsamples showed that teaching hospitals experienced no congestion loss. We found that quality of care could be improved by increasing the number of labor inputs in low-quality hospitals, whereas high-quality hospitals tended to have slack on personnel. Results suggest that reallocation of resources could increase the relative quality among hospitals in our sample. Further, higher quality in some dimensions of care need not be achieved as a result of higher costs or through reduced access to health care.

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.

Enhancement of TCP over wired/wireless networks with packet loss classifiers inferred by supervised learning

TCP is suboptimal in heterogeneous wired/wireless networks because it reacts in the same way to losses due to congestion and losses due to link errors. In this paper, we propose to improve TCP performance in wired/wireless networks by endowing it with a classifier that can distinguish packet loss causes. In contrast to other proposals we do not change TCP’s congestion control nor TCP’s error recovery. A packet loss whose cause is classified as link error will simply be ignored by TCP’s congestion control and recovered as usual, while a packet loss classified as congestion loss will trigger both mechanisms as usual. To build our classification algorithm, a database of pre-classified losses is gathered by simulating a large set of random network conditions, and classification models are automatically built from this database by using supervised learning methods. Several learning algorithms are compared for this task. Our simulations of different scenarios show that adding such a classifier to TCP can improve the throughput of TCP substantially in wired/wireless networks without compromizing TCP-friendliness in both wired and wireless environments.

Loss classification in optical burst switching networks using machine learning techniques: improving the performance of TCP

Optical burst switching (OBS) is considered as a contending technology for the core of the Internet in future. However, due to lack of the buffers, losses occur due to contention among simultaneously arriving bursts at the core nodes. Contention losses do not necessarily indicate a situation of congestion in the network. Thus differentiation (classification) of losses is essential in many applications to avoid false identification of congestion. In this paper, we propose a loss classification technique for the OBS networks based on machine learning techniques. We devise a new measure to differentiate between congestion and contention losses, which is derived from the observed losses, called the number of bursts between failures (NBBF). We observe that the NBBF follows a Gaussian distribution with different parameters for contention and congestion losses. This feature is used in differentiation. We use both a supervised learning technique (hidden Markov model (HMM)) and an unsupervised learning technique (expectation maximization (EM) clustering) on the observed losses and classify them into a set of states (clusters) after which an algorithm differentiates between the congestion and contention losses. We also demonstrate the use of loss differentiation in improving the performance of transport control protocol (TCP) over OBS networks. We modify congestion control mechanism of TCP suitably to arrive at two variants of TCP, HMM-TCP and EM-TCP. Their performance is compared with TCP NewReno, TCP SACK, and Burst TCP (X. Yu et al., Mar. 2004). Simulation results demonstrate the effectiveness and accuracy of the loss classification technique in different network scenarios.

Buffer Overflow Probability of TCP Flows During Mobile Handovers

Forwarding of user data is suspended for a short time at mobile handovers, but arriving packets are still buffered in the network. The resulting sudden peak in utilization may overflow the buffer, and the subsequent bursty packet loss will cause TCP connections to significantly degrade their throughput. We derive an analytical model for buffer overflow probability calculation, given the congestion window increase function and network parameters. Numeric results for current TCP variants and realistic network parameters show that congestion loss occurs with significant probability, even for very large buffer settings.

TCP CERL: congestion control enhancement over wireless networks

In this paper, we propose and verify a modified version of TCP Reno that we call TCP Congestion Control Enhancement for Random Loss (CERL). We compare the performance of TCP CERL, using simulations conducted in ns-2, to the following other TCP variants: TCP Reno, TCP NewReno, TCP Vegas, TCP WestwoodNR and TCP Veno. TCP CERL is a sender-side modification of TCP Reno. It improves the performance of TCP in wireless networks subject to random losses. It utilizes the RTT measurements made throughout the duration of the connection to estimate the queue length of the link, and then estimates the congestion status. By distinguishing random losses from congestion losses based on a dynamically set threshold value, TCP CERL successfully attacks the well-known performance degradation issue of TCP over channels subject to random losses. Unlike other TCP variants, TCP CERL doesn't reduce the congestion window and slow start threshold when random loss is detected. It is very simple to implement, yet provides a significant throughput gain over the other TCP variants mentioned above. In single connection tests, TCP CERL achieved an 175, 153, 85, 64 and 88% throughput gain over TCP Reno, TCP NewReno, TCP Vegas, TCP WestwoodNR and TCP Veno, respectively. In tests with multiple coexisting connections, TCP CERL achieved an 211, 226, 123, 70 and 199% throughput improvement over TCP Reno, TCP NewReno, TCP Vegas, TCP WestwoodNR and TCP Veno, respectively.

Enhancements on Router-Assisted Congestion Control for Wireless Networks

This paper addresses two challenges that are encountered when applying router-assisted explicit-feedback congestion control to wireless networks. The first challenge is how to distinguish between the two kinds of packet loss (non- congestion loss and congestion loss) in wireless networks and how to react to them properly. The second challenge is how to probe the unknown bandwidth capacity of wireless links which is required in calculating the router feedback. Some practical and novel enhancements on router-assisted congestion control in such environments are introduced in this paper. We have implemented these enhancements in a router-assisted congestion control protocol termed QFCP. Extensive simulation experiments using ns-2 will demonstrate that QFCP can fairly and efficiently allocate wireless bandwidth resources among competing flows in heterogeneous networks.

Robust end-to-end loss differentiation scheme for transport control protocol over wired/wireless networks

The authors propose a robust end-to-end loss differentiation scheme to identify the packet losses because of congestion for transport control protocol (TCP) connections over wired/wireless networks. The authors use the measured round trip time (RTT) values to determine whether the cause of packet loss is because of the congestion over wired path or regular bit errors over wireless paths. The classification should be as accurate as possible to achieve high throughput and maximum fairness for the TCP connections sharing the wired/wireless paths. The accuracies of previous schemes in the literature depends on varying network parameters such as RTT, buffer size, amount of cross traffic, wireless loss rate and congestion loss rate. The proposed scheme is robust in that the accuracy remains rather stable under varying network parameters. The basic idea behind the scheme is to set the threshold for the classification to be a function of the minimum RTT and the current sample RTT, so that it may automatically adapt itself to the current congestion level. When the congestion level of the path is estimated to be low, the threshold for a packet loss to be classified as a congestion loss is increased. This avoids unnecessary halving of the congestion window on packet loss because of the regular bit errors over the wireless path and hence improves the TCP throughput. When the congestion level of the path is estimated to be high, the threshold for a packet loss to be classified as the congestion loss not to miss any congestion loss is decreased and hence improves the TCP fairness. In ns 2 simulations, the proposed scheme correctly classifies the congestion losses under varying network parameters whereas the previous schemes show some dependency on subsets of parameters.

Mobile-Host-Centric Transport Protocol for<newline/>EAST Experiment

Some physics researchers retrieve EAST experiment data using the Transmission Control Protocol (TCP) in a wireless local area network (WLAN). TCP is the most commonly used transport control protocol. It assumes that every packet loss is caused by network congestion and invokes congestion control and avoidance. TCP's blind congestion control results in degraded performance in lossy wireless networks. In a wireless network, mobile hosts have first-hand knowledge of the lossy wireless links; therefore, mobile stations can make better transmission control based on the known status of wireless link. In this paper, we proposed a new mobile-host-centric transport protocol (MCP) that integrates the characteristics of sender-centric and receiver-centric transport control schemes. MCP shifts most control policies to the mobile host side. The general behavior of MCP is similar to the TCP, but by utilizing the local information collecting from the mobile node in WLAN, MCP allows for better congestion control and loss recovery. Specifically, we designed a cross-layer implementation of MCP and ran it on NS-2 network simulator. With valuable Medium Access Control (MAC) layer feedback information, MCP is able to distinguish packet loss caused by wireless random errors from network congestion more clearly and can perform a more accurate congestion control. We did extensive simulations of MCP on various WLAN scenarios, and the results show that the throughput of MCP with cross-layer feedback is higher than that of TCP Reno and Westwood.

MPTCP: How Can Route Diversity Improve the Internet Traffic?

This contribution aims to provide the fundamental basis of a new Transmission Control Protocol (TCP) designed for the next generation Internet. The TCP protocol is not capable to carry out all the growing traffic generated by the Internet as it leads to congestion and packet loss out of the quality of service specially required for critical connections. Moreover this behavior is accentuated in heavy load conditions. The Internet traffic becomes bursty and this trend is amplified as more participants contribute to generate data connections on a shared complex infrastructure. Therefore we focus on the design of a new protocol that aims to avoid or partially reduce the congestion appearance and the high variability of the Internet traffic. The stationarity of connection paths met on the Internet are judged responsible of the emergence of these characteristics. As a consequence a TCP-like protocol based on Multiple Paths (MPTCP) is suggested for a data transmission between two network entities in order to improve the QoS of the de¯ned connection. We propose there several algorithms that aim to extract multiple routes between two network components. This work is based on a theoretical modeling supported by simulations. Our network simulator is developed on top of the Scilab environment.

EJTCP: Enhanced Jitter-based TCP for Wireless Broadband Networks *

TCP is one of the most important and widely adopted transport protocols at present. With the advent of advanced wireless broadband technologies, TCP must be properly tuned and enhanced from traditional networks made up of purely wired links to wiredcum-wireless networks. As a result of high bit error rate (BER) in wireless links, TCP halves down its congestion window unnecessarily caused by random packet loss event continuously, and the performance is significantly degraded in wireless networks. The problem about differentiating congestion loss and random loss has been investigated recently by a number of wireless TCP solutions, such as JTCP (jitter-based TCP). While the existing solutions are accomplishing fundamental efforts to distinguish packet losses, some unavoidable events may occur to make TCP timeout frequently. Hence, we amend JTCP scheme to design a smooth transmission scheme to increase the correctness of loss distinction and avoid burst transmission. Besides, a novel channel aware scheme is designed to deal with dynamic modulation changing in 802.16 Wireless MAN. The experimental results show that our scheme, enhanced JTCP (EJTCP), unrolls significantly better performance than other algorithms over wired-cum-wireless network.

Enhancing Fairness and Throughput of TCP in Heterogeneous Wireless Access Networks

TCP exhibits inherent unfairness towards connections with Iong round-trip times and connections that have to traverse multiple congested routers. We have previously proposed a TCP bandwidth allocation (TBA) algorithm to solve this problem and proved its effectiveness in wireline networks. In this paper, we apply the IBA algorithm to improve TCP fairness over heterogeneous wireless networks with combined wireless and wireline links. In such networks, TCP suffers significant throughput degradations due to its window being frequently shut down, not in response to congestion, but by packet losses due to transmission errors over wireless links. We propose to apply wireless explicit congestion notification (WECN), a version of ECN enhanced for wireless networks, to decouple congestion control and loss recovery. Further enhancement is also incorporated to smooth traffic bursts. Simulation results show that not only can the combined TBA/WECN mechanism improve TCP fairness, but it can maintain good throughput performance in the presence of wireless losses as well.

TCP with header checksum option for wireless links: An analytical approach towards performance evaluation

TCP performs poorly in wireless mobile networks due to large bit error rates. Basically, the TCP sender responds to these losses as if they were due to congestion in the network, and reduces the congestion window unnecessarily. In earlier work, it has been shown that adding a TCP header checksum is very useful in differentiating between congestion loss and corruption loss. With the modified TCP, receivers can explicitly indicate corruption of received packets by generating “Explicit Loss Notifications (ELNs).” This paper focuses on an analytical study of this modified TCP protocol. We derive an expression for the probability of a receiver generating successful ELN, assuming a generic link layer protocol for data transfer over wireless links. Next, we develop an analytical approach for TCP throughput evaluation under the modified scheme. We compare the throughput results obtained by analysis and simulation, and find very close agreement between the two sets. We also compare the performance of the modified scheme with the standard NewReno TCP, and find considerable improvement in data throughput over wireless links.

Loss-cognizant pricing in networks with greedy users

We consider link pricing in packet-switched networks with fixed routing and random congestion losses. Network users are assumed to be greedy in the sense that each user increases its traffic rate in proportion to profit per packet it generates. The main goal of the paper is to devise pricing principles that maximize social welfare, which is taken as either the sum of goodputs or the sum of log-goodputs in the network. We adopt a deterministic fluid model whose analysis leads to pricing policies that stabilize packet generation rates at local maxima of social welfare for a rich set of network topologies. We also give decentralized algorithms to compute the price of packet forwarding at each link. Neither computation nor implementation of prices requires per-flow information. Obtained analytical results are verified via packet level simulations.

An enhancement of TCP veno over light-load wireless networks

This letter observes that TCP Veno behaves conservatively over light-load wireless networks. A new variable, congestion loss rate, is introduced into Veno's algorithm. It helps Veno deal with random loss more intelligently, by keeping its congestion window increasing if the link load is in light state. The simulation results demonstrate that, such enhancement can improve Veno's throughput up to 60% without any fairness or friendliness sacrificed

A network condition classification scheme for supporting video delivery over wireless Internet

Real-time video transport over wireless Internet faces many challenges due to the heterogeneous environment including wireline and wireless networks. A robust network condition classification algorithm using multiple end-to-end metrics and Support Vector Machine (SVM) is proposed to classify different network events and model the transition pattern of network conditions. End-to-end Quality-of-Service (QoS) mechanisms like congestion control, error control, and power control can benefit from the network condition information and react to different network situations appropriately. The proposed network condition classification algorithm uses SVM as a classifier to cluster different end-to-end metrics such as end-to-end delay, delay jitter, throughput and packet loss-rate for the UDP traffic with TCP-friendly Rate Control (TFRC), which is used for video transport. The algorithm is also flexible for classifying different numbers of states representing different levels of network events such as wireline congestion and wireless channel loss. Simulation results using network simulator 2 (ns2) showed the effectiveness of the proposed scheme.

TCP-Friendly Flow Control for Multimedia Streaming over Wired-to-Wireless IP Network

Current TCP-friendly congestion control mechanisms adjust the packet rate in order to adapt to wired network conditions and obtain a throughput not exceeding that of a TCP connection operating under the same conditions. However, these mechanisms can not be directly applicable to wireless network because there is no way to distinguish congestion losses from wireless channel losses. In this letter, a new loss differentiation algorithm for wired-to-wireless streaming service is described. The approach does not only adjust the sending rate according to the network status, but also provide the useful feedback to the video encoder.

Secure performance enhancing proxy: To ensure end-to-end security and enhance TCP performance over IPv6 wireless networks

It is a well known fact that TCP is incapacitated to distinguish congestion losses in the wired network from corruption losses occurring in the wireless link and this inability results in poor performance of TCP in a hybrid wired-cum-wireless scenario. Most of the solutions previously proposed to address this problem are designed oblivious of the security considerations and violate end-to-end TCP semantics. Achieving improved TCP performance together with ensuring end-to-end security necessitates the co-existence of security mechanisms like IPSEC and performance enhancing solutions. However, IP security and TCP performance have been traditionally dealt with in a mutually exclusive manner. We propose an innovative mechanism, Secure Performance Enhancing Proxy (SPEP), to address the seemingly arduous problem of enhancing TCP performance over wireless networks, preserving end-to-end TCP semantics as well as ensuring end-to-end security. The proposed SPEP scheme decouples error detection and error distinction mechanism from error recovery mechanism which not only facilitates in performance improvement but also offers multifarious advantages discussed in the paper. We have implemented the proposed scheme in FreeBSD 4.5 and conducted experiments in a controlled test bed setup. Our results show improved TCP performance in a secured environment with introduction of minimal overhead.

Performance analysis of double buffer technique (DBT) model for mobility support in wireless IP networks

Existing mobility support models in cellular communications misinterpret mobility loss in cellular networks as congestion loss, thus it degrades the performance by invoking unnecessary congestion control action. In this paper, we investigated the performance of Double Buffer Technique (DBT) model for mobility support in wireless IP networks. The DBT model uses the END message and the TQRS timer to maintain the packet sequence and decrease the load on the new foreign agent when the timer expires, respectively. Also, the protocol showed improved performance degradation caused by the handover of the mobile terminal. In order to demonstrate the superiority of our scheme over the existing ones, we used the following performance metrics: packet out-of-sequence, cell loss ratio, bandwidth overhead, and suitability for real-time services. The numerical results obtained revealed that the buffer size, the waiting time, and the packet loss probabilities in the model were suitable to the wireless IP environment.