P2P流媒体直播分布式缓存替换算法研究

P2P流媒体直播系统中分布式节点缓存区别于传统的Client/Server缓存结构,节点的实时同步给缓存管理提出较大挑战。分析了分布式缓存空间利用率的决定因素,通过节点成功请求比率,缓存的fresh度及数据分片点击率3个指标来评估节点缓存空间利用率,提出了频度限制与改进的LRU相结合的K-Degree&LRU2缓存替换算法。仿真实验结果表明,该算法较传统的FIFO、LRU算法具有更高的执行效率。     

Adaptive receiver-driven approach in P2P live streaming networks

Efficient delivery under changing network conditions is a major challenge in the design of live streaming systems. This study analyzes the key considerations and factors influencing live stream quality during system operations, and attempts to improve current P2P (peer-to-peer) live streaming systems by allowing users to enjoy high quality of service under the limitations of network resources. The proposed R-D (rate-distortion) optimized dynamic nodes join algorithm is based on multipath streaming concept and receiver-driven approach. This distributed algorithm enables the system to evaluate the current network status in order to optimize the end-to-end distortion of P2P networks. Experimental results of this study demonstrate the effectiveness of the proposed approach.     

Distributed optimization of P2P live streaming overlays

Peer-to-peer live media streaming over the Internet is becoming increasingly more popular, though it is still a challenging problem. Nodes should receive the stream with respect to intrinsic timing constraints, while the overlay should adapt to the changes in the network and the nodes should be incentivized to contribute their resources. In this work, we meet these contradictory requirements simultaneously, by introducing a distributed market model to build an efficient overlay for live media streaming. Using our market model, we construct two different overlay topologies, tree-based and mesh-based, which are the two dominant approaches to the media distribution. First, we build an approximately minimal height multiple-tree data dissemination overlay, called Sepidar. Next, we extend our model, in GLive, to make it more robust in dynamic networks by replacing the tree structure with a mesh. We show in simulation that the mesh-based overlay outperforms the multiple-tree overlay. We compare the performance of our two systems with the state-of-the-art NewCoolstreaming, and observe that they provide better playback continuity and lower playback latency than that of NewCoolstreaming under a variety of experimental scenarios. Although our distributed market model can be run against a random sample of nodes, we improve its convergence time by executing it against a sample of nodes taken from the Gradient overlay. The evaluations show that the streaming overlays converge faster when our market model works on top of the Gradient overlay.     

Enabling adaptive live streaming in P2P multipath networks

Live Internet streaming can be regarded as a major current multimedia delivery mode. Efficient delivery under changing network conditions is a severe challenge in the design of live streaming systems. This study analyzes the key considerations and factors influencing live stream quality during system operations, and attempts to improve present P2P (peer-to-peer) live streaming systems by allowing users to enjoy high quality of service under the limitations of network resources. The proposed R-D (Rate-Distortion) optimized-dynamic-nodes-join algorithm is based on multipath streaming concept and receiver-driven approach. This distributed algorithm enables the system to evaluate the current network status in order to optimize the end-to-end distortion of P2P networks and stay in the optimal status. Experiment results of this study demonstrate the effectiveness of the proposed approach.     

SmartPeerCast: a Smart QoS driven P2P live streaming framework

The P2P swarm technologies have been shown to be very efficient for medium scale content distribution systems in the last few years, such as the file sharing and video-on-demand (VOD) applications. However it is still an open topic about how to deploy the P2P paradigm for the real time video broadcasting (RTVB) applications. The P2P RTVB application is different from the cache based P2P system because it has more stringent restrictions for startup time and packet loss ratio. In this paper, an adaptive media broadcasting P2P framework named SmartPeerCast which employs the media transrating service to control the quality of service (QoS), is proposed. SmartPeerCast achieves a network awareness, codec awareness, and high performance RTVB service with four key designs: (1) It groups the newly joined peers into different quality clusters by their uploading capability. This clustering mechanism avoids the bandwidth bottleneck between the heterogeneous peers of the overall P2P overlay by only forwarding the same quality stream over the peers in the same cluster. (2) The streaming quality is adjusted adaptively between the sending and the receiving peers by a Smart QoS algorithm to compensate for the network jitters to reduce the receiving peer’s playback jitter. (3) The receiving peer monitors the data forwarding QoS of the sending peer to select the best suitable parent node dynamically. The SmartPeerCast uses this Smart QoS framework to implement an incentive mechanism to award the peers with high uploading contributions by migrating them to a higher quality cluster. (4) A transrating engine is used at the leaf nodes of the high quality cluster to forward the stream with suitable bits rate to the nodes of the low quality cluster; this transrating service not only can fully utilize the uploading bandwidth of the peers in the higher quality cluster but also avoids the bandwidth bottleneck of stream forwarding between the heterogeneous peers. Our experiment results and the real deployment show that SmartPeerCast can eliminate the bandwidth bottleneck and content bottleneck between the heterogeneous peers with a smaller startup time and packet loss and it is a high performance and medium scale P2P RTVB framework.     

Scalable playback rate control in P2P live streaming systems

Current commercial live video streaming systems are based either on a typical client–server (cloud) or on a peer-to-peer (P2P) architecture. The former architecture is preferred for stability and QoS, provided that the system is not stretched beyond its bandwidth capacity, while the latter is scalable with small bandwidth and management cost. In this paper, we propose a P2P live streaming architecture in which by adapting dynamically the playback rate we guarantee that peers receive the stream even in cases where the total upload bandwidth changes very abruptly. In order to achieve this we develop a scalable mechanism that by probing only a small subset of peers monitors dynamically the total available bandwidth resources and a playback rate control mechanism that dynamically adapts playback rate to the aforementioned resources. We model analytically the relationship between the playback rate and the available bandwidth resources by using difference equations and in this way we are able to apply a control theoretical approach. We also quantify monitoring inaccuracies and dynamic bandwidth changes and we calculate dynamically, as a function of these, the maximum playback rate for which the proposed system able to guarantee the uninterrupted and complete distribution of the stream. Finally, we evaluate the control strategy and the theoretical model in a packet level simulator of a complete P2P live streaming system that we designed in OPNET Modeler. Our evaluation results show the uninterrupted and complete stream delivery (every peer receives more than 99 % of video blocks in every scenario) even in very adverse bandwidth changes.     

P2P视频直播数据调度算法

P2P技术解决了传统流媒体应用中的不能支持大用户的问题.而数据调度算法一直是P2P研究中的热点问题.在给出了P2P视频直播系统中节点能力的定义和计算方法后,结合BT中的Rarest First策略,提出了一种基于节点能力的适用于P2P视频直播系统的数据调度算法.该算法既考虑了流媒体数据具有时间限制的特性,同时也考虑了如何能充分的利用节点的上传带宽,增进了系统的负载平衡.     

Game theoretic bandwidth procurement mechanisms in live P2P streaming systems

With the dramatic growth of Internet video streaming applications, resource provisioning for video streaming systems to satisfy their upload bandwidth deficit is a challenging task. The design of incentive mechanisms for taking advantage of unused upload capability of helper peers is proven to be a viable, cost-effective solution for this problem. The existing incentive mechanisms for video streaming systems do not consider the hierarchical nature of helper-server interactions, the limited budget of server to procure the needed bandwidth, and limited information of helpers about the other parties in the system. To address these issues, we designed cooperation mechanisms for two different cases: in the full-information case where the server has the full control over the amount of payments to each helper, a Stackelberg helping game is formulated in which the server as leader determines the amount of payment for each helper and then, helpers as followers decide on their amount of contributed bandwidth accordingly. We characterize the Stackelberg Equilibrium (SE) point of game in which the server shares the benefits of bandwidth sharing with the helpers through a market mechanism. In the partial information case where the helpers’ cost and utility functions are private and unknown to the server, we propose a budget-limited reverse auction in which the helpers, in contrast to the former case, announce the lowest price at which they are willing to sell their upload bandwidth first and the server then selects a subset of the helpers and pays them proportional to their contributions. The results of extensive simulations reveal that the mechanisms are truthful and result in lower server workload and higher peers’ streaming rate and delivery ratio.     

Enhancing P2P overlay network architecture for live multimedia streaming

The number of live multimedia streaming applications is increasing, explaining the use of many overlay network topologies. Application-layer multicast (ALM) that it is a feasible alternative to multimedia stream has attracted considerable attention. However, a serious problem of ALM is that the multicast tree may be fragile, and peer failure causes tree partitions. This work presents a novel Hierarchical Ring Tree (HRT) architecture for Peer-to-Peer (P2P) live multimedia streaming. The proposed architecture combines ring-based and tree-based structures in a robust, scalable, reliable and resilient structure that can be used practically as an ALM topology. When peers enter or leave the system, the topology can be recovered rapidly such that live multimedia stream can be delivered smoothly with a low latency. The proposed HRT topology is maintained efficiently without splitting or merging trees. The performance of the proposed architecture and algorithms is evaluated experimentally. Experimental results indicate that the proposed topology can be used in a high-churn P2P network with a small delay. Simulation and experiment results reveal that the proposed architecture has a lower overhead than the ZIGZAG approach when handling peers’ joining or leaving, exhibits faster recovery, better quality-of-service during streaming, and a more robust topology, even with an extremely high number of peers joining/leaving.     

QoS-awareness peer coordination control for topology-converging P2P live streaming

Multimedia Tools and Applications - For Peer to Peer (P2P) live streaming media, the peer coordination control mechanism becomes complex under dynamic traffic fluctuation, different node distance...     

Construction and maintenance of P2P overlays for live streaming

Multimedia Tools and Applications - P2P live streaming requires low latency and low media discontinuity to provide users good quality of experience. When peers are connected to a large number of...     

Characterizing peers communities and dynamics in a P2P live streaming system

Despite the large number of works devoted to understand P2P live streaming applications, most of them put forth so far rely on characterizing the static view of these systems. In this work, we characterize the SopCast, one of the most important P2P live streaming applications. We focus on its dynamics behavior as well as on the community formation phenomena. Our results show that SopCast presents a low overlay topology diameter and low end-to-end shortest path. In fact, diameter is smaller than 6 hops in almost 90 % of the observation time. More than 96 % of peers’ end-to-end connections present only 3 hops. These values combined may lead to low latencies and a fast streaming diffusion. Second, we show that communities in SopCast are well defined by the streaming data exchange process. Moreover, the SopCast protocol does not group peers according to their Autonomous System. In fact, the probability that a community contains 50 % of its members belonging to the same AS (when we observe the largest AS of our experiments) is lower then 10 %. Peers exchange more data with partners belonging to the same community instead of peers inside the same AS. For the largest AS we have, less than 18 % of peer traffic has been exchanged with another AS partners. Finally, our analysis provides important information to support the future design of more efficient P2P live streaming systems and new protocols that exploit communities’ relationships.     

基于Donet的P2P流媒体直播优化调度算法

为了提高P2P流媒体系统的整体性能,改善节点的播放质量,针对现有调度算法启动延迟大和节点带宽利用率不高问题,提出了一种可动态调节各节点中待请求紧急数据的流媒体直播优化调度算法(LOSA).该算法不仅考虑了流媒体直播的时间特性,同时还考虑了如何减少紧急数据请求的等待时间以及对Peer节点上传带宽的充分利用.实验结果表明,LOSA算法缩短了终端用户观看视频的延迟,提高了媒体流的连续性.     

基于多特征的P2P直播流识别方法

针对当前P2P流媒体直播流的识别方法较少、识别效果一般的问题,分析了P2P直播流的行为特征,提出了基于节点连接度的识别方法和基于BM信息比的识别方法,并结合两个流量特征采用联合特征进行P2P直播流识别。实验表明,该识别方法整体上识别准确率较高,可以实现P2P直播的在线识别。     

SimplyRep: A simple and effective reputation system to fight pollution in P2P live streaming

Peer-to-Peer (P2P) streaming has become a popular platform for transmitting live content. However, due to their increasing popularity, P2P live streaming systems may be the target of user opportunistic actions and malicious attacks, which may greatly reduce streaming rate or even stop it completely. In this article, we focus on a specific type of attack called content pollution, in which malicious peers tamper or forge media data, introducing fake content before uploading it to their partners in the overlay network. Specifically, we present a new decentralized reputation system, named SimplyRep, that quickly identifies and penalizes content polluters, while incurring in low overhead in terms of bandwidth consumption. We evaluate our method with both simulation and experiments in PlanetLab, comparing it against two previously proposed approaches, namely, a centralized black list and a distributed reputation system, in various scenarios. Our results indicate that SimplyRep greatly outperforms the two alternatives considered. In particular, both black list and the distributed reputation method perform poorly when polluters act jointly in a collusion attack, reaching a data retransmission overhead (triggered by polluted chunks received) of 70% and 30%, respectively, whereas the overhead experienced by SimplyRep is at most 2%. Our results also show that SimplyRep is able to quickly isolate almost all polluters under a dissimulation attack, being also somewhat robust to a whitewashing attack, although the latter remains a challenge to effective P2P streaming.     

A P4P-integrated data-driven P2P system for the live multimedia streaming service

The Proactive network Provider Participation for the P2P (P4P) architecture deploys central servers, which perceives network status and provides peering suggestions to P2P systems in order to achieve better network resource utilization while supporting best possible application performance. However, P4P alone may not be able to make appropriate peering suggestions for live multimedia streaming since it does not include mechanisms to reflect some of the parameters that are important to the QoS of live multimedia streaming such as upload bandwidth and stability of a peer as a stream deliverer. Furthermore, peer synchronization and parent replacement in the middle of a session, which are critical issues to the QoS of live multimedia streaming, are also left as the matters to be dealt with by the P2P systems alone. Most of the existing data-driven P2P systems leverage periodic information exchanges among neighboring peers in order to cope with these problems, which may incur long delay and high control overhead. In this paper, we proposed P4P-integrated data-driven P2P system for live multimedia streaming service. The proposed system includes not only the peering suggestion mechanism appropriate for live multimedia streaming but also the peer synchronization and parent replacement mechanisms, which exploit the centralized P4P framework and do not require periodic control information exchanges. We implemented the system in NS-2 simulator and compared its performance to the P4P and existing data-driven P2P systems. The results from experiments show that the proposed system enhances QoS compared to the existing data-driven P2P systems while maintaining the same level of network efficiency of the original P4P.     

基于P2PSIP的移动实时流媒体系统的安全架构

在分析移动实时流媒体应用对P2P环境提出的安全性方面挑战的基础上,提出了基于P2PSIP的移动实时流媒体系统MPSLSS的安全架构.针对MPSLSS系统的可管控性设计了一种分层混合式P2P网络架构,并采用STRIDE模型举例分析了MPSLSS系统面临的安全威胁,在此基础上提出了一种适用于移动实时流媒体应用的系统安全架构,并对其进行了分析.     

Hybrid fluid modeling approach for performance analysis of P2P live video streaming systems

In this paper a hybrid modeling approach with different modeling formalisms and solution methods is employed in order to analyze the performance of peer to peer live video streaming systems. We conjointly use queuing networks and Fluid Stochastic Petri Nets, developing several performance models to analyze the behavior of rather complex systems. The models account for: network topology, peer churn, scalability, peer average group size, peer upload bandwidth heterogeneity and video buffering, while introducing several features unconsidered in previous performance models, such as: admission control for lower contributing peers, control traffic overhead and internet traffic packet loss. Our analytical and simulation results disclose the optimum number of peers in a neighborhood, the minimum required server upload bandwidth, the optimal buffer size and the influence of control traffic overhead. The analysis reveals the existence of a performance switch-point (i.e. threshold) up to which system scaling is beneficial, whereas performance steeply decreases thereafter. Several degrees of degraded service are introduced to explore performance with arbitrary percentage of lost video frames and provide support for protocols that use scalable video coding techniques. We also find that implementation of admission control does not improve performance and may discourage new peers if waiting times for joining the system increase.     

Adaptive,incentive and scalable dynamic tree overlay for P2P live video streaming

In this paper, we propose a new multicast tree framework to be used in peer-to-peer (P2P) live video streaming systems. The proposed system, adapts the tree links under high peer churn and runs in a totally distributed manner. In order to provide this dynamism and seamless streaming at the same time, we propose a cross layer design involving scalable video codec, backup parents and hierarchical clusters. The performance of the system is measured in real world environment PlanetLab that has nodes distributed all over the world. The experiments show that the proposed system provides high quality of experience (QoE) in terms of Peak Signal to Noise Ratio (PSNR), playback delay and duration of pauses. The proposed system also provides incentive mechanism to its users.     

Service quality in P2P streaming systems

Relying on end users to contribute bandwidth to the system peer-to-peer (P2P) overlays provide a cheap and scalable way to distribute live video content in the Internet. However, being inherently dynamic due to peers joining and leaving the system at arbitrary time and running over the best-effort Internet, successful commercial usage of these systems may suffer from unstable media quality provided to end users. In this survey, we consider problems related to providing quality of media delivery in P2P streaming systems. We show that in spite of numerous systems available today no one incorporates mechanisms capable to maintain a certain level of quality of delivered media. We identify reasons behind that and discuss possible solutions to this problem.