TCP Window Size Research Articles

Effective Approach to Approximating TCP Window Size in High Latency Traffics

Effective Approach to Approximating TCP Window Size in High Latency Traffics

A study of IoT malware activities using association rule learning for darknet sensor data

Along with the proliferation of Internet of Things (IoT) devices, cyberattacks towards these devices are on the rise. In this paper, we present a study on applying Association Rule Learning to discover the regularities of these attacks from the big stream data collected on a large-scale darknet. By exploring the regularities in IoT-related indicators such as destination ports, type of service, and TCP window sizes, we succeeded in discovering the activities of attacking hosts associated with well-known classes of malware programs. As a case study, we report an interesting observation of the attack campaigns before and after the first source code release of the well-known IoT malware Mirai. The experiments show that the proposed scheme is effective and efficient in early detection and tracking of activities of new malware on the Internet and hence induces a promising approach to automate and accelerate the identification and mitigation of new cyber threats.

A Cross-Layer-Aware FDD/TDD Carrier Aggregation Framework for LTE-A Networks

In this paper, we study the aggregation between the frequency division duplex and time division duplex (TDD) spectrum bands within the context of 3GPP LTE-A system. To be specific, we first provide a cross-layer design analysis to obtain the achievable throughput using the TDD mode for transmission in LTE-A system. Under particular QoS requirements and certain channel conditions, the achievable throughput is derived and evaluated. The QoS requirements required from the upper layers, where the file size, the TCP window size and the latency for efficient transmission are incorporated in the final formulation. Having obtained the formulation, simulation results highlight the impact of the QoS parameters to different TDD frame format, wherein the number of DL and UL subframes vary. Having taken into account this design aspects, we propose a framework for TDD frame adaptation within the LTE-A system. The aim of this framework is to provide the dynamic configuration of different TDD frame formats by calculating the DL:UL subframes ratio under certain channel conditions and QoS requirements. We also provide flowchart procedures of how such a solution could be implemented within the 3GPP LTE-A context. Simulation results are carried out, which reveal the probability of choosing the different TDD frame formats from the system under certain channel conditions and QoS requirements.

Investigating the Network Characteristics of Two Popular Web-Based Video Streaming Sites

The determinants of the strategies to be employed by video streaming sites are application (mobile devices or web browsers) and container of the video application. They affect video streaming network characteristics, which is often the traffic flow, and its quality. It is against this background that studies on streaming strategies suggested the need to investigate and identify the relationship between buffer time, video stream protocol, packet speed and size, upload time, and waiting period, specifically to aid network administrative support in case of network traffic bottlenecks. In view of this, this study investigates the network characteristics of YouTube and Vimeo, using experimental methodology, and involving WireShark as network analyzer. Google Chrome and Firefox are the web browsers employed, while packet size, protocols, packet interval, TCP window size and accumulation ratio are the metrics. Short ON-OFF, Long ON-OFF, and No ON-OFF cycles are the three streaming strategies identified. It is further shown that both Vimeo and YouTube employ these strategies but the choice depends on the container of the video streamed.

Влияние размера TCP-окна на распределение интервалов между пакетами трафика в программно-конфигурируемых сетях SDN

This work considers effect of TCP-window size on the numerical characteristics of time slots between packets. Here we researched first three initial time slot moments due to developed mathematical model utilizes them. Researches were performed on virtual experimental setup installed over physical servers by OpenNebula platform. We considered two cases including software-defined network supporting OpenFlow open protocol and conventional network without it. The first one is performed with POX controller and physical switch. Here we utilize software products tcpdump for traffic capture and Iperf for traffic generation. This work presents script providing traffic generation initiation process automation. Obtained results were imported to MS Excel. Then moment characteristics are evaluated by well-known mathematical statistics formulas.

Optimising network transfers to and from Queen Mary University of London, a large WLCG tier-2 grid site

Optimising network performance is key to high bandwidth data transfers required for a Tier-2 site. We describe the techniques we have used to obtain good performance. Monitoring plays a key part, as does the elimination of bottlenecks and tuning TCP window sizes. Multiple parallel transfers allowed us to saturate a l Gbit/s link for 24 hours - whilst still achieving acceptable download speeds. Source based routing and multiple data transfer servers allowed us to use an otherwise unused "resilient" link.

A Simple Solution to Find the Distribution of TCP Window Sizes

The performance of Internet applications depends very much on the dynamics of TCP congestion window sizes. This paper presents a novel model of TCP congestion window sizes. In particular, we focus on the multiplicative-decrease phases of the TCP congestion window instead of additive-increase phases. With this focus, we derive a model and a novel solution for finding the distribution of TCP window sizes. Both simulations and experiments show that our proposed model and solution are accurate.

A robust active queue management scheme for network congestion control

Active queue management has been proved to be an effective mechanism at the intermediate nodes to alleviate network congestion. A novel robust active queue management scheme based on H-infinity feedback control theory is proposed in this paper. A TCP model with link capacity disturbances, modeling uncertainties and time-varying delay is investigated, and the objective is to design a feedback controller which guarantee the queue length stability and robustness against the external disturbances and model perturbations. Meanwhile a simple on-line estimation of TCP window size is adopted instead of state observer which reduces computation burden significantly. The controller parameters are obtained through the standard linear matrix inequality techniques. Finally NS-2 simulation results demonstrate effectiveness of the proposed method.

Total variation estimates for the TCP process

The TCP window size process appears in the modeling of the famous Transmission Control Protocol used for data transmission over the Internet. This continuous time Markov process takes its values in [0, ∞), is ergodic and irreversible. The sample paths are piecewise linear deterministic and the whole randomness of the dynamics comes from the jump mechanism. The aim of the present paper is to provide quantitative estimates for the exponential convergence to equilibrium, in terms of the total variation and Wasserstein distances.

Data uploading time estimation for CUBIC TCP in long distance networks

CUBIC is a TCP-friendly algorithm that uses a cubic curve, independent of the round-trip time, to rapidly recover from a packet loss. New releases of Linux use CUBIC for the TCP protocol. In this paper, we show that if the socket buffer size of a sender TCP is small compared with the bandwidth-delay product, Linux TCP window size drops to almost zero every time a packet loss occurs. Using this fact, we estimate data uploading time in long distance networks with packet loss. Also we discuss the improvement of the uploading time by increasing cumulative socket buffer size in two ways: large buffer size or parallel connections.

TCP-based window-size delegation method for TXOP Exchange in wireless local area networks

We propose a TCP window-size delegation method for downlink TXOP (transmission opportunity) Exchange in wireless local area networks (WLANs). In our method, the 'compliant' stations (STAs) cooperatively use their available bandwidth in accordance with their throughput demand. We realize our method only with minimal modifications of the TCP functions of a proxy server, which lets one station (the TXOP provider) delegate TCP window size to another station (the TXOP client) so that the provider delegates its TXOPs in WLANs to the client. Our method enables an STA to flexibly delegate TXOPs to another STA without adversely affecting the legacy STAs, which is confirmed by computer simulations. We also confirmed that our method requires no modification to legacy access points and STAs.

Weighted Window and Class-Based Weighted Window Methods for Per-Station TCP Fairness in IEEE 802.11 WLANs

TCP unfairness problem in access networks using the 802.11 has been studied by many researchers. Their solutions required that the existing MAC protocol be modified. However, since they did not consider the case when each wireless node has a different number of flows, they cannot provide fairness among wireless nodes having different numbers of flow in both directions. In order to resolve this problem, Weighted Window and Class-Based Weighted Window methods are proposed. In the Weighted Window method, each wireless node can control the rate of TCP flows based on TCP window size. By applying this method, per-station fairness can be achieved, regardless of the number and direction of flows in each wireless node. Furthermore, to improve and to provide fair bandwidth allocation in the Weighted Window method when the users have different requirements, the Class-Based Weighted Window method is proposed. Therefore, for wireless nodes with different requirements, fair allocation bandwidth between wireless nodes in the same class of bandwidth is achieved.

On the long time behavior of the TCP window size process

The TCP window size process appears in the modeling of the famous transmission control protocol used for data transmission over the Internet. This continuous time Markov process takes its values in [ 0 , ∞ ) , and is ergodic and irreversible. It belongs to the additive increase–multiplicative decrease class of processes. The sample paths are piecewise linear deterministic and the whole randomness of the dynamics comes from the jump mechanism. Several aspects of this process have already been investigated in the literature. In the present paper, we mainly get quantitative estimates for the convergence to equilibrium, in terms of the W 1 Wasserstein coupling distance, for the process and also for its embedded chain.

Data transfer over the wide area network with a large round trip time

A Tier-2 regional center is running at the University of Tokyo in Japan. This center receives a large amount of data of the ATLAS experiment from the Tier-1 center in France. Although the link between the two centers has 10Gbps bandwidth, it is not a dedicated link but is shared with other traffic, and the round trip time is 290ms. It is not easy to exploit the available bandwidth for such a link, so-called long fat network. We performed data transfer tests by using GridFTP in various combinations of the parameters, such as the number of parallel streams and the TCP window size. In addition, we have gained experience of the actual data transfer in our production system where the Disk Pool Manager (DPM) is used as the Storage Element and the data transfer is controlled by the File Transfer Service (FTS). We report results of the tests and the daily activity, and discuss the improvement of the data transfer throughput.

A novel Markov analytical model for the TCP/AQM systems

A novel closed-loop feedback TCP/AQM (Transfer Control Protocol/Active Queue Management) model is proposed in this paper using a discrete-time Markov chain, and a way to calculate the equilibrium distribution of this model is given. In the model, system time is divided into time slots, the bottleneck router queue model and TCP window size model in each slot are analyzed. Finally, by combining adjacent slots, an integrated TCP/AQM analytical model is developed. By this model, the average values of packets dropping ratio and queue length in the router and TCP sending rate can be estimated, hence, this model could be a useful tool for the analysis of AQMs and support the development of new AQM schemes theoretically. The proposed TCP/AQM model is extended to a TCP-UDP (Control User Datagram Protocol)/AQM model, to analyze the TCP/AQM system performance when UDP flows exist. By implementing this model on Matlab, we compare its solutions to NS2 simulated solutions, then the validity of the model to analyze the closed-loop feedback TCP/RED (Random Early Detection) system is verified.

Routing exploiting multiple heterogeneous wireless interfaces: A TCP performance study

This paper proposes a routing scheme that exploits multiple heterogeneous wireless interfaces on a node: a primary 802.11a interface and a secondary 802.11b (or 802.11) interface. In normal conditions, a TCP flow uses a primary path over the 802.11a interface discovered by a reactive routing protocol. But in presence of route breakage due to node mobility, it resorts to its backup path over the 802.11b interface which is already maintained by a proactive routing protocol and is being used for delivery of control or management packets. The secondary interface exhibits different property than the primary interface (i.e., slower rate but larger transmission range). This helps keep TCP flows alive and preserve the TCP window size, thereby making them more resilient to route breakage induced by mobility. ns-2 implementation and simulations reveal several potential benefits of the proposed routing scheme: (1) recovering packets immediately in the event of link failures, (2) maintaining TCP connections while the higher-rate 802.11a path is not available, and even making the 802.11a path more available, (3) preserving the TCP window size during route breakage, which can lead to preservation of throughput, especially when the round trip delay between a source and a destination is large (e.g., either for long-hop connections or in high queueing delay conditions caused by network congestion, or both).

WITHDRAWN: On the long time behavior of the TCP window size process

WITHDRAWN: On the long time behavior of the TCP window size process

Transient Moments of the TCP Window Size Process

The TCP window size process can be modeled as a piecewise-deterministic Markov process that increases linearly and experiences downward jumps at Poisson times. We present a transient analysis of this window size process. Our main result is the Laplace transform of the transient moments. Formulae for the integer and fractional moments are derived, as well as an explicit characterization of the speed of convergence to steady state. Central to our approach are the infinitesimal generator and Dynkin's martingale.

Transient Moments of the TCP Window Size Process

The TCP window size process can be modeled as a piecewise-deterministic Markov process that increases linearly and experiences downward jumps at Poisson times. We present a transient analysis of this window size process. Our main result is the Laplace transform of the transient moments. Formulae for the integer and fractional moments are derived, as well as an explicit characterization of the speed of convergence to steady state. Central to our approach are the infinitesimal generator and Dynkin's martingale.

A Design of Gain-scheduled Congestion Controllers using State Predictive Observers

Abstract In this paper, a design problem of congestion controllers is discussed for TCP/AQM(Transmission Control Protocol/Active Queue Management) networks. The proposed method consists of two control techniques. First one is based on a gain-scheduling technique considering nonlinearities of TCP/AQM networks. But the designed congestion controller is a state feedback controller and it is impossible to embed the congestion controller in real computer networks. To avoid this problem, second one is based on a design technique of state predictive observer for linear time-delay systems. Thus it can be possible to embed the congestion controller in real networks by combining these methods. Firstly dynamical models of TCP/AQM are described as linear systems with self-scheduling parameters, which also depend on information delay. Here it is distinguishing to focus on constraints on the maximum queue length and TCP window-size, which are the network resources in TCP/AQM networks. And a design method of memoryless state feedback controllers is shown for linear system with a self-scheduling parameter and an information delay. But the designed gain- scheduled congestion controller is a state feedback controller and it is impossible to apply this controller to computer networks directly. Thus observers are also designed and the observer-based congestion controllers are derived.