基于BitTorrent的激励机制的研究与改进

BitTorrent系统面临着严重的搭便车问题。研究BitTorrent系统的搭便车问题及其激励机制,对P2P文件共享系统有重要意义。介绍当前BitTorrent系统激励机制的研究现状,分析BitTorrent文件共享系统的搭便车现象及其激励机制,提出了一个种子带宽分配策略。通过模拟实验实现了该策略,并分析了模拟实验的结果。     

Optimizing BitTorrent-like peer-to-peer systems in the presence of network address translation devices

BitTorrent nowadays is one of the most important peer-to-peer (P2P) file-sharing applications on the Internet, and it has also inspired many other P2P applications such as live or on-demand video streaming services. On the other hand, Network Address Translation (NAT) has become pervasive in almost all networking scenarios, from residential Internet access to enterprise networks. Despite the effort of NAT traversal, it is still very likely that P2P applications cannot receive incoming connection requests properly if they are behind NAT. To quantify the performance impact of NAT on BitTorrent-like P2P systems, we have created and validated a detailed but tractable mathematical model. We have also proposed and briefly examined a simple but effective strategy to mitigate the negative impact on NAT peers. In this paper, we further extend our model to cover the proposed biased optimistic unchoke strategy, and optimize the system performance in terms of both average peer download time and system finish time. We also create a new, faster Java-based BitTorrent simulator, which is used to validate the extended model and show the optimality of the proposed strategy and its boundary conditions.     

Towards efficient video chunk dissemination in peer-to-peer live streaming

There are substantial differences in chunk dissemination manner between P2P live streaming and BitTorrent, and inappropriate algorithms will result in inefficiency of live streaming systems. In this paper, we study the chunk dissemination of P2P live streaming, and introduce a discrete and slotted mathematical model to analyze chunk selection algorithms, including rarest first algorithm and greedy algorithm. Moreover, we present a performance metric to evaluate chunk selection algorithms, as well as the optimization function for the exploration of chunk dissemination strategies. We point out the causes of poor performance of these algorithms, and propose a service request randomization mechanism to promote the use of peer resources, which can prevent chunk requests from rendezvous on a few of peers. Simultaneously, we employ weight assignment strategies to avoid excessive requests for rare chunks. Besides, we present an enhanced model, which adds node degree constraint, to improve our model. We revisit the chunk selection algorithms based on the enhanced model. The results of simulation experiments validate our theoretical analysis and indicate that the weighted randomization mechanism is resilient to flash crowd and peer churn, and can improve the performance of P2P live streaming.     

Free-Riding on BitTorrent-Like Peer-to-Peer File Sharing Systems: Modeling Analysis and Improvement

BitTorrent has emerged as a very popular peer-to-peer file sharing system, which uses an embedded set of incentive mechanisms to encourage contribution and prevent free-riding. However, the capability BitTorrent has of preventing free-riding needs further study. In this paper, we present a fluid model with two different classes of peers to capture the effect of free-riding on BitTorrent-like systems. With the model, we find that BitTorrent's incentive mechanism is successful in preventing free-riding in a system without seeds, but may not succeed in producing a disincentive for free-riding in a system with a high number of seeds. The reason for this is that BitTorrent does not employ any effective mechanisms for seeds to effectively guard against freeriding. Therefore, we propose a seed bandwidth allocation strategy for the BitTorrent system to reduce the effect of seeds on free-riding. Finally, simulation results are given, which validate what we have found in our analysis and demonstrate the effectiveness of the proposed strategy.     

K网络节点标识符重复与别名现象测量

为方便P2P网络的内容投递,Kademlia协议作为一个鲁棒性强的分布式Hash表协议,被BitTorrent和eMule等P2P文件共享应用部署.在此,将这些被部署的基于Kademlia协议的网络称为K网络.K网络中每个节点拥有唯一的IP地址(或ID)是至关重要的,因为K网络中的"节点查询"和"资源搜索"都依赖于此.然而,据分析发现,K网络中相当一部分节点存在IP重复与ID别名.为深入理解IP重复与ID别名的分布特征,提出了几个度量IP重复与ID别名的测度.基于这些测度和Rainbow采集器,对K网络中的IP重复与ID别名进行了测量,发现了许多有助于P2P网络挖掘研究的IP重复与ID别名特征.     

一种缩短下载时间优先的自适应BitTorrent激励协议

BitTorrent激励机制的目标是保证节点上传和下载之间的公平性,但相比公平性而言,实际应用中的节点更优先考虑的是文件下载时间,据此文中提出了一种缩短文件下载时间优先的自适应BitTorrent激励协议AIPS.文中首先基于Markov模型对BitTorrent现有激励机制的效果给出了定量分析,分析了激励机制下的文件传输结构,并用概率分析方法给出了该传输结构下最小化文件下载时间的条件.应用分析结果文中定义了一个以缩短文件下载时间为效用的博弈,在该博弈达到Nash平衡时各节点采用的策略就是激励协议AIPS.模拟实验表明文中提出的AIPS较现有的BitTorrent激励协议能明显提高文件共享系统性能,提高文件下载效率.     

An incentive scheduling mechanism for peer-to-peer video streaming

P2P video streaming networks are found as a scalable solution and an alternative for traditional client–server based video streaming over the Internet. One of the significant issues affecting the success of any P2P streaming network is cooperation between peers. Practical observations have proved the prevalence of free riders in P2P networks that degrade their performance. To solve this problem, using incentive mechanisms, which encourage peers to contribute more in the network, is necessary. In this paper, we designed and proposed a distributed and scalable incentive mechanism for mesh based P2P video streaming networks. In the proposed approach the contribution of the peers is measured and maintained in a distributed fashion. Furthermore, we proposed an incentive sending side scheduler in which peers are served based on their contribution in the network. Our simulation evaluations show the efficiency of the proposed approach in improving the overall perceived video quality by the non-free rider nodes and consequently in the whole network.     

DHT网络基于债务关系的公平文件交换

P2P(peer to peer)网络中,节点的自私行为极大地降低了系统的可用性.基于债务关系的文件交换网络,构建了一种促进合作的激励机制.同时,该机制保证了文件交换的公平性.激励机制的关键在于DHT(distributed hash table)网络邻居有限的固有特征,因而节点间的交互易于形成重复博弈.DFFE(debt relationship based fair file exchange in DHT network)协议只需维护很少的本地节点交互信息,协议开销小、网络扩展性好.网络路由采用基于一跳信息的贪婪算法.理性节点间的博弈存在纳什均衡,其策略选择的近似算法具有渐进收敛性.仿真实验表明了激励机制的有效性和在动态网络中性能的稳定性.     

BitTorrent协议中激励机制的设计与分析

激励机制是BitTorrent协议的重要组成部分,它鼓励用户上传以获得更快的下栽速度,并提高系统整体性能。原有BitTorrent激励机制存在大量的搭便车节点,极大影响了激励效果,因此提出了一种新的激励策略,并给出了具体的实施算法。对应用这种新激励机制的BitTorrent协议进行了详细的着色Petri网（colored Petri nets,CPN）形式化建模分析,在验证模型正确性的基础上,进行基于模型模拟的性能分析实验,结果表明该激励机制能够严格限制搭便车节点行为,达到更好的激励效果。     

An incentive mechanism to reinforce truthful reports in reputation systems

The success of current trust and reputation systems is on the premise that the truthful feedbacks are obtained. However, without appropriate mechanisms, in most reputation systems, silent and lying strategies usually yield higher payoffs for peers than truthful feedback strategies. Thus, to ensure trustworthiness, incentive mechanisms are highly needed for a reputation system to encourage rational peers to provide truthful feedbacks. In this paper, we model the feedback reporting process in a reputation system as a reporting game. We propose a wage-based incentive mechanism for enforcing truthful report for non-verifiable information in self-interested P2P networks. A set of incentive compatibility constraint rules including participation constraint and self-selection constraints are formulated. We design, implement, and analyze incentive mechanisms and players’ strategies. The extensive simulation results demonstrate that the proposed incentive mechanisms reinforce truthful feedbacks and achieve optimal welfare.     

Evaluating stranger policies in P2P file-sharing systems with reciprocity mechanisms

How to deal with strangers efficiently is a big challenge for designing P2P systems, as ineffective stranger policies will cause the degradation of system performance and fairness. In this work, we focus on an open P2P file-sharing environment with reciprocity incentive mechanisms, and we evaluate the impact of different stranger policies to system performance and fairness using both numerical analyses and agent-based simulations. The results reveal that there exist tradeoffs between system performance and fairness; the optimal performance and fairness of the system cannot be reached simultaneously; free-riders will survive when system performance is optimal. The accuracy of this evaluation is verified through the analysis of stranger policies in BitTorrent and eMule/eDonkey. Therefore, this evaluation can effectively help P2P designers select appropriate stranger policies according to their individual design goals.     

BitTorrent协议Choking／Unchoking机制的度量和分析

BitT0rrent是一个用于内容分发的P2P协议,现在已经发展成为互联网的一项重要的应用.本文从性能的角度,度量BitTorrent的行为,解释BitTorrent协议的关键元素,分析BitTorrent是否是高效的.本文有以下贡献:①提出一种有效度量BitTorrent式的内容分发协议的方法.②确认BitTorrent的Choking/Unchoking机制存在缺陷,不是高效的.③设计ShareStorm协议,证明BitTorrent的缺陷可以避免.经初步验证,在下载完成时间这个最主要的性能指标上,ShareStorm比BitTbrrent至少减少50 %.     

Modeling resource constrained BitTorrent proxies for energy efficient mobile content sharing

In this paper we present a solution that makes BitTorrent content transfer for mobile device more energy efficient. The main idea of the research is that instead of downloading the content via BitTorrent directly to the mobile phone, an intermediate proxy is used which sends the data to the phone in high speed bursts. This results in smaller energy footprint compared with regular BitTorrent data transfer. Furthermore, we focus on how the proxy can be hosted on memory limited broadband routers which are available in almost every home. We define an analytical model which can be used to analyze the memory allocation strategies of the proxy peers and predict how proxy peers influence the P2P community performance. We verify our model via simulations. We also present measurement results with real life torrents using our prototype system running on home routers and Symbian based mobile phones.     

Downloading trace study for BitTorrent P2P performance measurement and analysis

With the increasing client population and the explosive volume of Internet media content, the peer-to-peer networking technologies and systems provide a rapid and scalable content distribution mechanism in the global networks. The BitTorrent protocol and its derivatives are among the most popular peer-to-peer file sharing applications, which contribute a dominant fraction of today??s Internet traffic. In this paper, we conduct the performance measurement and analysis of BitTorrent systems with an extensive volume of real trace logs. We use several downloading-side metrics, including overall downloading time, maximum of downloading bandwidth, average bandwidth utilization, maximum of downloading connections, and average number of active connections, to derive various interesting results from the downloading-side aspect of network resource usage. Performance examination learns many new observations and characteristics into the virtue of BitTorrent protocols and systems, thereby providing beneficial information for bandwidth allocation and connection control in BitTorrent client applications. Therefore, this study is complementary to many previous research works that mainly focused on system-oriented and uploading-side performance measurements.     

Revisiting free riding and the Tit-for-Tat in BitTorrent: A measurement study

In this paper we report new results of our continuous effort on analyzing the impact of incentive mechanisms on user behavior in BitTorrent. In this second measurement and analysis study we find that free riders’ population has significantly increased comparing to our previous measurement study. We relate this increase to the advance in end-users’ connection speeds and to users’ increased knowledge in BitTorrent. We also categorize free riders based on the behavior they exhibit in multiple-torrent system into three types: cheaters, strategic and lucky peers. Furthermore, refuting the findings of other studies, we show that peers who exploit the system in BitTorrent are both high bandwidth capacity peers and low bandwidth capacity peers. Moreover, we argue that the Tit-for-Tat mechanism does not discriminate peers based on their bandwidth capacities and that it reacts successfully against inter-class bandwidth capacity strategic peers. Finally, we propose a memory-backoff approach to the optimistic unchoke policy that reduces the volume of free riding in BitTorrent.

Optimal scheduling of peer-to-peer file dissemination

Peer-to-peer (P2P) overlay networks such as BitTorrent and Avalanche are increasingly used for disseminating potentially large files from a server to many end users via the Internet. The key idea is to divide the file into many equally-sized parts and then let users download each part (or, for network coding based systems such as Avalanche, linear combinations of the parts) either from the server or from another user who has already downloaded it. However, their performance evaluation has typically been limited to comparing one system relative to another and has typically been realized by means of simulation and measurements. By contrast, we provide an analytic performance analysis that is based on a new uplink-sharing version of the well-known broadcasting problem. Assuming equal upload capacities, we show that the minimal time to disseminate the file is the same as for the simultaneous send/receive version of the broadcasting problem. For general upload capacities, we provide a mixed integer linear program (MILP) solution and a complementary fluid limit solution. We thus provide a lower bound which can be used as a performance benchmark for any P2P file dissemination system. We also investigate the performance of a decentralized strategy, providing evidence that the performance of necessarily decentralized P2P file dissemination systems should be close to this bound and, therefore, that it is useful in practice. Research of G. Weiss is supported in part by Israel Science Foundation Grants 249/02 and 454/05. Collaboration of the authors was supported in part by European Network of Excellence Euro-NGI.     

A mathematical analysis of the cumulus pricing scheme

One important task in current and future communication networks is to define a suitable pricing scheme. It is then preferable to formulate a mathematical model, so that parameters will be optimized and important properties such as fairness or truthful anticipated load revelation (or incentive compatibility) will be verified. In this paper we study a simple and promising scheme called the cumulus pricing scheme, which can address service differentiation and scalability among other issues. Based on a mathematical model, we determine values for optimizing the provider’s revenue, which happens under the constraint that each user has an incentive to reveal its anticipated load. This has led to a small variation of the initial model from the literature as in the modelling, cumulus points are translated into financial terms, and measurements induce a cost as well.     

Improving sustainability of BitTorrent darknets

Private BitTorrent community, known as “BitTorrent Darknet” or “Private Tracker (PT)”, has received much attention in the research literature recently. Different from public BitTorrent community, PT can only be accessed by its registered members, and it can provide ultra-high downloading speed due to its effective Sharing Ratio Enforcement (SRE) incentive mechanism which stimulates members to contribute content as much as possible. Although the downloading performance in PTs with high Seeder-to-Leecher Ratio (SLR) is much better than in public BitTorrent communities, our measurements show that SRE mechanism can induce “Poor Downloading Motivation” problem for members who want to increase their sharing ratios to survive and thrive in PT. This problem may discourage PT members’ enthusiasm from contributing to community. To improve sustainability of PTs, we adopt the Predator–prey model to analyze high SLR phenomenon, study the optimal stable SLR range to PTs. Moreover, we develop a queuing model to simulate the seeding/leeching process in a single torrent in PT, and try to maximize the swarming performance with minimum seeding peers. This solution can help PT achieve the optimal SLR range.     

Shape equilibrium constraint: a strategy for stress-constrained structural topology optimization

In topology optimization of a continuum, it is important to consider stress-related objective or constraints, from both theoretical and application perspectives. It is known that the problem is challenging. Although remarkable achievements have been made with the SIMP (Solid Isotropic Material with Penalization) framework, a number of critical issues are yet to be fully resolved. In the paper, we present an approach of a shape equilibrium constraint strategy with the level-set/X-FEM framework. We formulate the topology optimization problem under (spatially-distributed) stress constraints into a shape equilibrium problem of active stress constraint. This formulation allows us to effectively handle the stress constraint, and the intrinsic non-differentiability introduced by local stress constraints is removed. The optimization problem is made into one of continuous shape-sensitivity and it is solved by evolving a coherent interface of the shape equilibrium concurrently with shape variation in the structural boundary during a level-set evolution process. Several numerical examples in two dimensions are provided as a benchmark test of the proposed shape equilibrium constraint strategy for minimum-weight and fully-stressed designs and for designs with stress constraint satisfaction.     

PS2P网络中视频点播系统的设计与实现*

结合视频点播应用的具体需求,对BitTorrent协议中的分片选择策略、激励机制进行改进,并融合媒体服务器对资源的下载支持,实现了基于PS2P的视频点播系统HyBT。性能分析表明,HyBT能在保证音/视频内容高速传输的前提下,减少点播缓冲时间,使音/视频内容流畅播放,让用户获得良好的视听体验和服务质量。