Performance analysis of BitTorrent-like systems with heterogeneous users

Among all peer-to-peer (P2P) systems, BitTorrent seems to be the most prevalent one. This success has drawn a great deal of research interest on the system. In particular, there have been many lines of research studying its scalability, performance, efficiency, and fairness. However, despite the large body of work, there has been no attempt mathematically to model, in a heterogeneous (and hence realistic) environment, what is perhaps the most important performance metric from an end user’s point of view: the average file download delay.

In this paper we propose a mathematical model that accurately predicts the average file download delay in a heterogeneous BitTorrent-like system. Our model is quite general, has been derived with minimal assumptions, and requires minimal system information. Then, we propose a flexible token-based scheme for BitTorrent-like systems that can be used to tradeoff between overall system performance and fairness to high bandwidth users, by properly setting its parameters. We extend our mathematical model to predict the average file download delays in the token- based system, and demonstrate how this model can be used to decide on the scheme’s parameters that achieve a target performance/fairness.     

Improving fairness in IEEE 802.11 networks using MAC layer opportunistic retransmission

This paper introduces DAFMAC (Decode And Forward MAC), a scalable opportunistic cooperative retransmission enhancement for the IEEE 802.11 MAC protocol which operates without the need for additional explicit control signalling. Distributed opportunistic retransmission algorithms rely on selecting a single suitable relay without direct arbitration between nodes. Simulations show that DAFMAC offers a significant improvement in fairness for both throughput and jitter, giving multiple parallel data flows a more equal opportunity to utilise the channel. DAFMAC cooperative retransmissions are shown to reduce node energy consumption for a given throughput. Further, the DAFMAC relay selection algorithm is shown to scale very well in terms of complexity and memory requirements in comparison to other cooperative retransmission schemes.     

FluidSim: a tool to simulate fluid models of high-speed networks

In this paper, we present a tool for the simulation of fluid models of high-speed telecommunication networks. The aim of such a simulator is to evaluate measures which cannot be obtained through standard tools in reasonable time or through analytical approaches. We follow an event-driven approach in which events are associated with rate changes in fluid flows. We show that under some loose restrictions on the sources, this suffices to efficiently simulate the evolution in time of fairly complex models. Some examples illustrate the utilization of this approach and the gain that can be observed over standard simulation tools.     

Heterogeneous-aware cache partitioning: Improving the fairness of shared storage cache

In this paper, we investigate the problem of fair storage cache allocation among multiple competing applications with diversified access rates. Commonly used cache replacement policies like LRU and most LRU variants are inherently unfair in cache allocation for heterogeneous applications. They implicitly give more cache to the applications that has high access rate and less cache to the applications of slow access rate. However, applications of fast access rate do not always gain higher performance from the additional cache blocks. In contrast, the slow application suffer poor performance with a reduced cache size. It is beneficial in terms of both performance and fairness to allocate cache blocks by their utility.In this paper, we propose a partition-based cache management algorithm for a shared cache. The goal of our algorithm is to find an allocation such that all heterogeneous applications can achieve a specified fairness degree as least performance degradation as possible. To achieve this goal, we present an adaptive partition framework, which partitions the shared cache among competing applications and dynamically adjusts the partition size based on predicted utility on both fairness and performance. We implement our algorithm in a storage simulator and evaluate the fairness and performance with various workloads. Experimental results show that, compared with LRU, our algorithm achieves large improvement in fairness and slightly in performance.     

The effect of contention in CSMA networks: Model and fairness protocol

Multi-hop wireless networks using Carrier Sense Multiple Access (CSMA) suffer from various forms of unfairness. A majority of the existing work focuses on fairness issues due to hidden terminals and the impact on backoff mechanisms. This paper focuses on a more fundamental form of unfairness that arises due to unequal contention opportunities at a node; some nodes rarely observe an idle channel since two or more interferers can transmit together. Contention unfairness is unrelated to hidden terminals. The paper analyzes the impact of contention and provides insight into developing solutions for contention unfairness. We first develop a model-from first principles-for contention in IEEE 802.11 networks. The accuracy of the model is validated through simulations and the results show that such unfairness is a common phenomenon. Based on the insights gained from the model, we propose and evaluate distributed schemes that reduce the effect of unfairness due to contention. We show that contention unfairness occurs frequently in general scenarios. Simulation results indicate that the proposed protocols improve the overall system performance by providing greater fairness with a small reduction in throughput.     

Performance sensitivity and fairness of ECN-aware ‘modified TCP’

The paper discusses how explicit congestion notification (ECN) can be used to devise an Internet congestion control mechanism that is more rapidly reactive and allows best-effort flows to rapidly adjust to fluctuations in available capacity. Our ECN-mod protocol involves simple modifications to TCP behavior and leverages more aggressive marking-based router feedback. Simulations show that ECN-mod is better than TCP NewReno for both persistent sources and Web-style intermittent traffic sources, and makes the link utilization significantly less sensitive to the variation in the number of active flows. Simulations also show that, while ECN-mod flows obtain a larger portion of the available capacity than conventional best-effort traffic, they do not starve or significantly penalize such TCP-based flows.     

Discrete bandwidth allocation considering fairness and transmission load in multicast networks

As a promising solution to tackle the network heterogeneity in multicasting, layered multicast protocols such as receiver-driven layered multicast (RLM) and layered video multicast with retransmission (LVMR) have been proposed. This paper considers fairness as well as transmission load in the layered multicasting. Lexicographically fair bandwidth allocation among multicast receivers is considered under the constraint of minimum bandwidth requirement and the link capacity of the network. The problem of transmission load in the layer multicasting due to various user requirements is also examined by minimizing the number of layers.     

Improving TCP fairness and performance with bulk transmission control over lossy wireless channel

The traditional windows-based TCP congestion control mechanism produces throughput bias against flows with longer packet roundtrip times; the flow with a short packet roundtrip time preoccupies the shared network bandwidth to a greater extent than others. Moreover, the blind window reduction that occurs whenever packets are lost decreases the network utilization severely, especially in networks with high packet losses. This paper proposes a sender-based TCP congestion control, called TCP-BT. The scheme estimates the network bandwidth depending on the transmission behavior of applications, and adjusts the congestion window by considering both the estimated network bandwidth and the packet roundtrip time to improve fairness as well as transmission performance. The scheme has been implemented in the Linux platform and compared with various TCP variants in real environments. The experimental results show that the proposed scheme improves transmission performance, especially in networks with congestion and/or high packet loss rates. Experiments in real commercial wireless networks have also been conducted to support the practical use of the proposed mechanism.     

An approximate compositional approach to the analysis of fluid queue networks

Fluid models have for some time been used to approximate stochastic networks with discrete state. These range from traditional ‘heavy traffic’ approximations to the recent advances in bio-chemical system models. Here we present a simple approximate compositional method for analysing a network of fluid queues with Markov-modulated input processes at equilibrium. The idea is to approximate the on/off process at the output of a queue by an n-state Markov chain that modulates its rate. This chain is parameterised by matching the moments of the resulting process with those of the busy period distribution of the queue. This process is then used, in turn, as a separate Markov-modulated on/off process that feeds downstream queue(s). The moments of the busy period are derived from an exact analytical model. Approximation using two- and three-state intermediate Markov processes are validated with respect to an exact model of a tandem pair of fluid queues — a generalisation of the single queue model. The analytical models used are rather simpler and more accessible, albeit less general, than previously published models, and are also included. The approximation method is applied to various fluid queue networks and the results are validated with respect to simulation. The results show the three-state model to yield excellent approximations for mean fluid levels, even under high load.     

An accurate performance model for network-on-chip and multicomputer interconnection networks

In this paper, we present a mathematical background for a new approach for performances modeling of interconnection networks, based on analyzing the packet blocking and waiting time spent in each channel passing through all possible paths in the channel dependency graph. We have proposed a new, simple and very accurate analytical model for deterministic routing in wormhole networks, which is general in terms of the network topology and traffic distribution. An accurate calculation of the variance of the service time has been developed, which overcomes the rough approximation used, as a rule, in the existing models. The model supports two-dimensional mesh topologies, widely used in network-on-chip architectures, and multidimensional topologies, popular in multicomputer architectures. It is applicable even for irregular topologies and arbitrary application-specific traffic. Results obtained through simulation show that the model achieves a high degree of accuracy.     

Analyzing the performance of a cluster-based architecture for immersive visualization systems

Cluster computing has become an essential issue for designing immersive visualization systems. This paradigm employs scalable clusters of commodity computers with much lower costs than would be possible with the high-end, shared memory computers that have been traditionally used for virtual reality purposes. This change in the design of virtual reality systems has caused some development environments oriented toward shared memory computing to require modifications to their internal architectures in order to support cluster computing. This is the case of VR Juggler, which is considered one of the most important virtual reality application development frameworks based on open source code.     

BitTorrent模型的信任机制研究

BitTorrent下载模型得到普遍的应用,但节点缺乏控制,存在虚假资源等安全性问题。针对BitTorrent下载模型的特点,分析了BitTorrent模型的安全问题所在及已有的BitTorrent安全防范机制,结合P2P技术中的信任模型思想,改进BitTorrent安全机制,优化文件的拆分和整合算法,提高下载资源的成功率。仿真实验表明,与传统BitTorrent下载模型相比,改进后的模型能较快发现网络中的虚假资源,具有更高的下载成功率。     

通用绩效模型的设计与实现

从实践的角度,运用系统的方法,在研讨当前绩效管理过程的基础上提出了通用绩效模型.在通用绩效模型的实现方面,引入了指标的概念,运用了业务规则方法原理.通用绩效模型的设计与实现简化了绩效管理系统的设计,使得绩效管理的可操作性、可执行性更强,方便了企业的管理.     

Feature detection using the general linear model

The detection of simple features using position-invariant filters constructed by the use of the matched filter theorem is extended to the general case of features with more than one free parameter.     

Exhaustive fluid vacation model with positive fluid rate during service

Using an elegant transform domain iterative operator approach exhaustive fluid vacation models with strictly negative fluid rate during service have been analyzed, recently. Unfortunately, the potential presence of positive fluid rate during service (when the fluid input rate is larger than the fluid service rate) inhibits the use of all previously applied methodologies and makes the extension of the analysis approaches of discrete vacation and polling models towards fluid vacation and polling models rather difficult.Based on the level crossing analysis of Markov fluid models the paper introduces an analysis approach which is applicable for the stationary analysis of the fluid level distribution and its moments. In the course of the analysis compact new matrix exponential expressions are obtained for the distribution of fluid level during a busy period starting from a given positive fluid level and by exploiting the relations of upward and downward measures of fluid processes several matrix transformations are applied to avoid Kronecker expansion matrix multiplications.Finally, the obtained fluid level distribution is related with previous results of fluid vacation models.     

On the performance of a hybrid network traffic model

We study a hybrid network traffic model that combines a fluid-based analytical model using ordinary differential equations with the packet-oriented discrete-event simulation. The hybrid model is important to large-scale real-time network simulations, where the packet-level emulation traffic is handled by discrete events and the majority of the background traffic is described more efficiently as fluids. We present a simple performance analysis of this hybrid approach. We propose three techniques—namely, pointer caching, update dampening, and dynamic time stepping—in an implementation of the hybrid model. Experiments show that these techniques can significantly improve the performance of the fluid-based network simulation.     

Inversion of a velocity model using artificial neural networks

We present a velocity model inversion approach using artificial neural networks (NN). We selected four aftershocks from the 2000 Tottori, Japan, earthquake located around station SMNH01 in order to determine a 1D nearby underground velocity model. An NN was trained independently for each earthquake-station profile. We generated many velocity models and computed their corresponding synthetic waveforms. The waveforms were presented to NN as input. Training consisted in associating each waveform to the corresponding velocity model. Once trained, the actual observed records of the four events were presented to the network to predict their velocity models. In that way, four 1D profiles were obtained individually for each of the events. Each model was tested by computing the synthetic waveforms for other events recorded at SMNH01 and at two other nearby stations: TTR007 and TTR009.     

On the performance of bandwidth and storage sharing in information-centric networks

Information Centric Network (ICN) proposals, have recently emerged to define new network architectures where content, and not its location, becomes the core of the communication model. Such new paradigms push data storage and delivery at network layer and are designed to cope with current Internet usage, mainly centered around content dissemination and retrieval.     

基于神经网络的三维模型视觉特征分析

首先从形状、颜色、纹理材质三个主要视觉特性入手,阐述模型的特征描述符,设计三元组视觉特征向量用于神经网络进行模型分类。具体基于感知器神经网络、Hopfield神经网络分别实现了对三维物体的分类。实验表明,基于神经网络的分类器能对基于视觉特征描述的三维物体进行有效识别。     

Preserving global features of fluid animation from a single image using video examples

We synthesize animations from a single image by transferring fluid motion of a video example globally.Given a target image of a fluid scene,an alpha matte is required to extract the fluid region.Our method needs to adjust a user-specified video example for producing the fluid motion suitable for the extracted fluid region.Employing the fluid video database,the flow field of the target image is obtained by warping the optical flow of a video frame that has a visually similar scene to the target image according to their scene correspondences,which assigns fluid orientation and speed automatically.Results show that our method is successful in preserving large fluid features in the synthesized animations.In comparison to existing approaches,it is both possible and useful to utilize our method to create flow animations with higher quality.