Hardware-Based TCP Processor for Gigabit Ethernet

Classical Transmission Control Protocol (TCP) designs have never considered the identity of the competing transport protocol as useful information to TCP sources in congestion control mechanisms. When competing against a TCP flow on a bottleneck link, a User Datagram Protocol (UDP) flow can unfairly occupy the entire link bandwidth and suffocate all TCP flows on the link. If it were possible for a TCP source to know the type of transport protocol that deprives it of link access, perhaps it would be better for the TCP source to react in a way which prevents total starvation. In this paper, we use coefficient of variation and power spectral density of throughput traces to identify the presence of UDP transport protocols that compete against TCP flows on bottleneck links. Our results show clear traits that differentiate the presence of competing UDP flows from TCP flows independent of round-trip times variations. Signatures that we identified include an increase in coefficient of variation whenever a competing UDP flow joins the bottleneck link for the first time, noisy spectral density representation of a TCP flow when competing against a UDP flow in the bottleneck link, and a dominant frequency with outstanding power in the presence of TCP competition only. In addition, the results show that signatures for congestion caused by competing UDP flows are different from signatures due to congestion caused by competing TCP flows regardless of their round-trip times. The results in this paper present the first steps towards development of more ’intelligent’ congestion control algorithms with added capability of knowing the identity of aggressor protocols against TCP, and subsequently using this additional information for rate control.

TCP (transmission control protocol) is the prevalent reliable transport protocol used for many of the Internet's most popular services like Web browsing and e-mail. Since these services are the dominant applications on the Internet, TCP can be said to control the large majority of today's Internet traffic and we can say the enhancement of TCP performance means the improvement of the most Internet performance. In this paper, we compare various ACK generation TCP strategies that play very important roles in TCP operation and propose advanced delayed ACK algorithms to mitigate the negative effect of delayed ACK algorithm. Even if delayed ACK has a bright side to save network resources and power consumption that are the very important factors especially for mobile and wireless environments, it has also a dark side not to take full advantage of network bandwidth in the slow start phase. It is reported that delayed ACK timeout of the first and last segment causes a severe degradation problem in TCP throughput performance. We suggest new algorithms to solve delayed ACK penalty and to guarantee fairness with other traffic in slow start. In wired-cum-wireless network environments, BADA (base station aided delayed ACK) with SNDA (sender notification delayed ACK), the combination of our proposed algorithm shows the best performance in terms of throughput as well as in terms of network resource sharing. Our simulation shows significantly improved performance in TCP throughput.

Throughput and fairness performance of transmission control protocol (TCP) worsens critically under vehicular environment due to its weakly bounded congestion threshold parameter, rate reduction approach and congestion recovery algorithm. In this paper, a new congestion control algorithm for vehicular networks, called VC-TCP (Vehicular customized -TCP) is proposed to overcome the limitations of the existing independent congestion control approaches. The VC-TCP implements a newer congestion threshold parameter, which regulates the spurious rate reduction due to an abrupt increase in RTT spike value. During the congestion control process, VC-TCP uses a new recovery algorithm and bandwidth utilization based rate reduction, which substantially improves the flow fairness of TCP traffic flows with different bandwidth utilization levels. The throughput, flow fairness, and packet latency performances of VC-TCP is evaluated against the standard Vegas congestion control approach under simulated vehicular scenarios. The simulation outcomes verify the performance improvement of the proposed VC-TCP approach against the standard TCP variants in the different facets of the vehicular environment.

We propose a packet-level model to investigate the impact of channel error on the transmission control protocol (TCP) performance over IEEE-802.11-based multihop wireless networks. A Markov renewal approach is used to analyze the behavior of TCP Reno and TCP Impatient NewReno. Compared to previous work, our main contributions are listed as follows: 1) modeling multiple lossy links, 2) investigating the interactions among TCP, Internet Protocol (IP), and media access control (MAC) protocol layers, specifically the impact of 802.11 MAC protocol and dynamic source routing (DSR) protocol on TCP throughput performance, 3) considering the spatial reuse property of the wireless channel, the model takes into account the different proportions between the interference range and transmission range, and 4) adopting more accurate and realistic analysis to the fast recovery process and showing the dependency of throughput and the risk of experiencing successive fast retransmits and timeouts on the packet error probability. The analytical results are validated against simulation results by using GloMoSim. The results show that the impact of the channel error is reduced significantly due to the packet retransmissions on a per-hop basis and a small bandwidth delay product of ad hoc networks. The TCP throughput always deteriorates less than ~ 10 percent, with a packet error rate ranging from 0 to 0.1. Our model also provides a theoretical basis for designing an optimum long retry limit for IEEE 802.11 in ad hoc networks.

In this paper, we develop a model-based frame scheduling scheme, called MFS, to enhance the capacity of IEEE 802.11-operated wireless local area networks (WLANs) for both transmission control protocol (TCP) and user datagram protocol (UDP) traffic. In MFS each node estimates the current network status by keeping track of the number of collisions it encounters between its two consecutive successful frame transmissions, and computes accordingly the current network utilization. The result is then used to determine a scheduling delay to be introduced before a node attempts to transmit its pending frame. MFS does not require any change in IEEE 802.11, but instead lays a thin layer between the LL and medium access control (MAC) layers. In order to accurately calculate the current utilization in WLANs, we develop an analytical model that characterizes data transmission activities in IEEE 802.11-operated WLANs with/without the request to send/clear to send (RTS/CTS) mechanism, and validate the model with ns-2 simulation. All the control overhead incurred in the physical and MAC layers, as well as system parameters specified in IEEE 802.11, are figured in. We conduct a comprehensive simulation study to evaluate MFS in perspective of the number of collisions, achievable throughput, intertransmission delay, and fairness in the cases of TCP and UDP traffic. The simulation results indicate that the performance improvement with respect to the protocol capacity in a WLAN of up to 300 nodes is 1) as high as 20% with the RTS/CTS and 70% without the RTS/CTS in the case of UDP traffic and 2) as high as 10% with the RTS/CTS and 40% without the RTS/CTS in the case of TCP traffic. Moreover, the intertransmission delay in MFS is smaller and exhibits less variation than that in IEEE 802.11; the fairness among wireless nodes in MFS is better than, or equal to, that in IEEE 802.11.

Applications operating over airborne networks are known to perform quite sub-optimally. Transmission Control Protocol (TCP) based applications often experience very low data throughput [1], while the User Datagram Protocol (UDP) based applications suffer high packet loss as well as out-of-order delivery [2]. This is due to the high Bit Error Rate (BER) nature of the wireless links and the high mobility of airborne nodes. Though TCP and UDP have performed well in wired networks, their original design did not take into consideration the characteristics seen in airborne networks thus resulting in their relatively poor performance. In this research, we implemented an OPNET model of the Reliable User Datagram Protocol (RUDP) as proposed in the IETF Internet-Draft in 1999 [3] with extensions to take into consideration the nature of airborne network characteristics. We then analyzed the performance and its applicability to airborne network scenarios. We also provide performance comparison of the enhanced RUDP against the TCP, UDP, and the standard RUDP counterparts.

The increase in demand for proper and fast access to network infrastructure around the University environment by staff, students, and visitors in the quest to carry out daily tasks or keeping up with trends/innovations around the globe is a daily experience resulting in some challenges. But these challenges are not unexpected. The access to network infrastructure around the environment encourages proper development. This paper presents an empirical observation of transmission control protocol upstream throughput (TCPupT) and downstream throughput (TCPdownT) performance for an IEEE 802.11g wireless local area network (WLAN) installed at a corridor space of University of Nigeria, Nsukka campus. This work measured the TCP upstream and downstream throughput values for single, double, and multiple users (several Users) accessing an installed WLAN access point. The paper adopted basic WLAN system setup approach while observing the TCP performance in relation to SNR. Data collected for each environment were statistically analyzed, equations and results were also presented. The observed TCP throughput values vary as users increase thereby affecting the observed round-trip time (RTT). The generated equations were also used to predict TCP throughput which would aid network engineers in the deployment of IEEE 802.11g WLAN systems especially around the university environment. It is now clear that the generated model equations can be used for predicting the expected performance of IEEE 802.11g WLAN systems during deployment. This work gives WLAN engineers, researchers and users an apparatus to rapidly estimate the TCP upstream and downstream throughput, by monitoring the received SNR for IEEE 802.11g systems.

TCP (Transmission Control Protocol) Vegas congestion control algorithm is studied comprehensively in ad hoc networks. Based on Vegas algorithm, a new improved Vegas3 algorithm is presented. During the congestion avoidance, the improvement measure is to divide communication conditions of networks into more particular states; then to take special countermeasure for special communication condition. This algorithm integrates Vegas and Vegas-A algorithm into one algorithm, and adjusts the parameters alpha and beta of Vegas dynamically for adapting to the change of network conditions. The adjusting of alpha and beta, the dividing of network conditions, and the implementing of different measure, all as far as possible accord with originally Vegas algorithm strategy. The result of our simulation shows that the Vegas3 algorithm is superior to Vegas and Vegas-A algorithm in TCP throughput.

LTE standard provides different Quality of Service (QoS) options which enable to provide multiple services to the User Equipment (UE). Design of scheduling algorithm for Transmission Control protocol (TCP) based traffic is challenging in wireless networks. Many papers have been developed to improve the throughput of TCP traffic. In this work, a novel and practically feasible scheduling algorithm is proposed to handle the TCP traffic in order to improve the overall LTE cell and UE throughput. An uplink grant is provided at the time of scheduling Downlink (DL) TCP traffic for acknowledgement transfer which minimizes TCP throughput fluctuations which improves cell and per UE throughput. The amount of advanced uplink grant can be computed using Kalman filter algorithm by considering real time reported parameters as per LTE standard. The proposed algorithm is implemented in small cell platform and real time results are generated. It shows that significant gain is achieved in throughput under specific traffic conditions.

Recently, dynamic adaptive streaming over HTTP (DASH) has become an increasingly popular way to view video over the Internet. In particular compared to other video streaming services these DASH approaches deliver superior QoE to viewers. This is due to improved video segment selection. Generally, Transmission Control Protocol (TCP) CUBIC is the defacto transport layer protocol use by DASH. To improve the robustness of the transport layer to network congestion many other TCP variants were implemented such as Compound TCP and BBR. Nevertheless some were made to work specifically in LAN environments for example Agile-SD. However, recently another transport layer protocol User Datagram Protocol (UDP) has been used in Google’s QUIC implementation. To date no work has be found giving the performance of these transport layer protocols with DASH. In this paper we test the performance of Agile-SD, CUBIC, Compound TCP, BBR and QUIC using the BBA, MPC, Pensieve and Oboe DASH approaches. Experiments simulate congested bottleneck link conditions common at household routers where families view multiple videos at the same time. We observe Oboe and Agile-SD is the most promising combination with CUBIC and Pensieve next. However, even though QUIC was touted to have superior transport layer performance by Google it was the worst performing.

The transmission control protocol (TCP) was designed to provide reliable end-to-end delivery of data over unreliable networks. Most TCP implementations have been carefully optimised to operate in wired networks. Deploying standard TCP in wireless mobile ad hoc networks (MANETs) can lead to poor performance of TCP. The main problem that faces TCP in ad hoc networks is its inability to distinguish between packet losses due to congestion and those due to route failures. In order to adapt TCP to MANET environment, several TCP improvements that differentiate between different types of packet losses using explicit notification messages from lower layers have been proposed. In this paper, we propose a new end-to-end technique that does not require any participation from intermediate nodes within the network. The proposed scheme relies on expanding the retransmission timeout (RTO) interval in order to reduce the number of timeouts that do not result from congestion. Simulation results show that our scheme can improve TCP throughput and delay. It outperformed the standard TCP in detailed simulation experiments.

In this paper, we present preliminary results of our ongoing networked virtual reality project by discussing the implementation and performance of a networked haptic game. In this game, online players feel like handling a real basketball since they are able to feel the sense of touch by using haptic interfaces. One of challenging issues in this implementation is haptic data transmission over the Internet to allow online multi-user play. Since haptic information is extremely sensitive to delay and jitter, the provision of timely transmission is critical. We carry out experiments to compare the performance of the haptic data transmission when using UDP (User Datagram Protocol) and TCP (Transmission Control Protocol), and observe that neither UDP nor TCP is able to satisfy QoS (Quality of Service) requirements of the haptic transmission. As a further study, we plan to investigate some alternative haptic data transmission schemes.

The object of research is Markov models of network nodes with UDP (User Datagram Protocol) and TCP (Transmission Control Protocol) traffic and their differences. The task solved is the lack of Markov models of network nodes describing the behavior of TCP traffic from the point of view of packet retransmissions and packet delivery guarantees. Markov models of network nodes describing traffic behavior with guaranteed packet delivery have been further advanced. Given the comparison of the models, the differences from the classic models serving TCP traffic were shown, for each packet flow, an additional dimensionally was added to the graph of states and transitions, which takes into account the retransmission of a lost packet. The comparison graph shows similar behavior of queue length and packet loss for both types of traffic. But the nature of the curves is different. With TCP traffic, packet loss can exceed 5 percent. In addition, lost packets must be retransmitted, which increases the load on the network node. More failures and packet queue lengths at a network node during peak load typically occur with TCP traffic compared to UDP traffic. At peak load, the difference in service failures can reach 20–30 percent. The main reason is that TCP uses flow control and rate-limiting mechanisms to avoid network congestion and ensure efficient data transfer between nodes. The Markov model of TCP traffic requires an additional dimensionally on the graph of states and transitions, which affects the behavior of queues and packet failures. The investigated problem was solved due to the universality and diversity of the mathematical apparatus of Markov mass service systems. The results could be used in network modeling software products for building and reengineering the topology of electronic communications networks at enterprises and organizations

An intermediate node in an inter-flow network coding scheme needs to know exactly which are the previous hop and next hop of a packet before coding. It is difficult to incorporate inter-flow network coding into opportunistic routing (OR) because the next hop of a packet in OR can't be determined in advance. Coding-aware opportunistic routing (CAR) is proposed in this paper to address this problem on fixed wireless mesh networks (WMNs). Meanwhile, it aims to maximize the number of native packets coded in each single transmission. It dynamically selects a route for a given flow according to the real-time coding opportunities. There are no control packets in CAR, which greatly reduces the overhead costs. CAR gives the coded packet that consists of a larger number of native packets with a smaller forwarding delay. The forwarder with the largest number of native packets coded together is ultimately selected to send data. Simulations demonstrate that CAR achieves significantly better throughput gains and derives a reasonable end-to-end delay in both cross topology and mesh topology under both transmission control protocol (TCP) and user datagram protocol (UDP) traffic, as explained below. CAR achieves more than 35 % throughput improvement under TCP traffic and more than 15 % throughput improvement under UDP traffic, compared to other state-of-art protocols in cross topology, respectively. CAR also provides a several-fold increase in throughput in a large scale network (mesh topology). In a word, CAR significantly improves network performance of a WMN.

SCTP is a transport layer protocol mainly designed for transferring public switched telephone network signalling over IP networks. Some of the protocols that support data transmission are transmission control protocol (TCP), user datagram protocol (UDP), and stream control transmission protocol (SCTP). SCTP is a newly invented reliable, message-oriented transport protocol. It is similar to TCP and UDP with some additional features such as multi-streaming and multi-homing. Even though it is a new protocol with some advanced features, there is a security loophole issue in data transmission using SCTP. Hence, we proposed a new technique to transmit a secret message by hiding it in a secret matrix using the advanced features of SCTP. The simulation of our proposed method provides better performance and high security for secret message transmission against network attacks.