P2P systems require neighbor peers to frequently exchange buffer-map (BM) messages for efficient content sharing and distribution, which, however, can result in considerable communication overhead. A big problem in the BMs exchanged between neighbor peers is that a lot of information in them is redundant. To reduce the redundancy, some P2P systems have adopted certain block-level compression schemes (e.g., Huffman encoding) to compress each BM in isolation. However, these schemes simply treat each BM separately and as a single block of data, which largely affects their compression efficiency. In this paper, we propose a novel relevant-window-based (RW) compression framework, which takes advantage of the correlation between sequentially exchanged BMs between neighbor peers and thus can greatly remove the redundancy in them. We accordingly design a RW-based distributed compression scheme, which can work alone or co-work well with an existing block-level compression scheme for higher compression efficiency. We prove the correctness of our scheme and derive tight upper bound on average length of compressed bitmaps by our scheme via mathematical modeling. Numerical results demonstrate that our scheme alone can achieve compression efficiency of 96.6%, which can be further increased to up to 97.1% when jointly working with a block-level compression scheme.

A peer-to-peer (P2P) live streaming system faces a big challenge under flash crowds. When a flash crowd occurs, the sudden arrival of numerous peers may starve the upload capacity of the system, hurt its quality of service, and even cause system collapse. This paper provides a comprehensive study on the performance of P2P live streaming systems under flash crowds. By modeling the systems using a fluid model, we study the system capacity, peer startup latency, and system recovery time of systems with and without admission control for flash crowds, respectively. Our study demonstrates that, without admission control, a P2P live streaming system has limited capacity to handle flash crowds. We quantify this capacity by the largest flash crowd (measured in shock level) that the system can handle, and further find this capacity is independent of system initial state while decreasing as departure rate of stable peer increases, in a power-law relationship. We also establish the mathematical relationship of flash crowd size to the worst-case peer startup latency and system recovery time. For a system with admission control, we prove that it can recover stability under flash crowds of any sizes. Moreover, its worst-case peer startup latency and system recovery time increase logarithmically with the flash crowd size. Based on the analytical results, we present detailed flash crowd handling strategies, which can be used to achieve satisfying peer startup performance while keeping system stability in the presence of flash crowds under different circumstances .

Multiparty video conferencing (MPVC) facilitates real-time group interaction between users. While P2P is a natural delivery solution for MPVC, a peer often does not have enough bandwidth to deliver her video to all other peers in the conference. Recently, we have witnessed the popularity of one-view MPVC, where each user only watches full video of another user. One-view MPVC opens up the design space for P2P delivery. In this paper, we explore the feasibility of a pure P2P solution for one-view MPVC. We characterize the video source rate region achievable through video relays between peers. For both homogeneous and heterogeneous MPVC systems, we establish tight universal video rate lower bounds that are independent of the number of peers, the number of video sources, and the specific viewing relations between peers. We further propose, P2P video relay designs to approach the maximal video rate region. Through numerical simulations, we verified that the derived lower bounds are indeed tight bounds, and the proposed bandwidth allocation algorithm can achieve a close-to-optimal peer upload bandwidth utilization. Our results demonstrate that P2P is a promising solution for one-view MPVC. Insights obtained from our study can be used to guide the design of P2P MPVC systems.

In this paper, we measure and study the peer startup process in PPLive, a popular commercial P2P streaming system, and focus on a fundamental issue in this aspect: how a peer initializes its buffer when it joins a channel, i.e., initial offset placement of peers' buffers in the startup stage. We build a general model of peer startup process in chunk-based P2P streaming systems and present an initial offset placement scheme we inferred from the measurement results, i.e., proportional placement (PP) scheme. With FP scheme, the initial buffer offset is set to the offset of the reference neighbor peer plus an advance proportional to the reference neighbor peer's offset lag or buffer width. We evaluate the performance of PP scheme and find it is stable when the placement is based on offset lag, but will be unstable when it is based on buffer width if the chunk fetching strategy and neighbor peer selection mechanism are not properly designed. We finally report our detailed measurement results of the peer startup process and initial offset placement algorithms used in PPLive. Our models and measurement results could be useful for guiding the analysis and design of buffering protocols for a real P2P live streaming system.

In P2P video-on-demand (VoD) streaming system, aggregate download bandwidth of users fluctuates significantly because of peer departure, bandwidth heterogeneity and network delay. The playback rate of videos also fluctuates in order to attain constant image quality. These two kinds of dynamics cause playback interruptions. Prefetching some video content before playback is an effective method to offset the adverse effect of dynamics. In this paper, we choose the number of interruptions in a viewing process as the metric of user perceived QoS (UPQoS). Then we propose a stochastic model to relate the UPQoS with some important system parameters, such as playback rate, downloading speed and prefetched content volume (PCV). It is found that reducing the system dynamics or increasing the PCV or aggregate download bandwidth can improve UPQoS. Besides, the interruption occurs at the beginning of a viewing process with great probability; a few users suffer many interruptions in a viewing process while most of users experience no interruption. Finally, we do a large scale network measurement towards PPLive VoD streaming system and the measurement result is consistent with the conclusion got from this model.

A fundamental problem that a peer-to-peer (P2P) live streaming system faces is how to support flash crowds effectively. A flash crowd occurs when a burst of join requests arrive at a system. When a flash crowd occurs, the sudden arrival of numerous peers may starve the upload capacity of a P2P system, and degrade the quality of service. By theoretical analysis and simulations, we find that a system has limited capacity to handle a flash crowd: It can recover to a new stable state when the size of flash crowd is small or moderate, but collapse when the flash crowd is excessively large. The capacity of a system is independent of initial state of the system while relevant to stable peers' departure rate, which suggests this capacity is an essential property of a P2P live streaming system. In addition, we prove that a P2P live streaming system with admission control has excellent capacity to handle flash crowds: It can recover from flash crowds of excessively large size and a startup peer's waiting time scales logarithmically with the size of flash crowds. Our theoretical model and simulation results provide a promising framework to understand the capacity of a P2P live streaming system for handling flash crowds.

In a peer-to-peer (P2P) live streaming system, peer requests collide when multiple peers request data pieces from the same peer (or media server). When collisions occur, some of the peers' requests fail and retries have to be taken, which delays peer's receipts of pieces. This paper shows that request collisions occur frequently at both media servers and peers, and have big impact on system performance. It then proposes two algorithms to address this issue. The first is a novel admission control algorithm at the media server. The second is a peer selection algorithm in which peer requests pieces from neighbors with low collision probability. Simulation results show that the proposed algorithms improve system performance significantly.

In this paper, a new four-antenna based structure (FAS) is introduced for capacity improvement in future cellular networks with frequency reuse factor of 1. In FAS, each cell consists of one omni-directional antenna located at the cell center and three 120-degree directional antennas located at the cell edge. In order to achieve effective system bandwidth allocation among four antennas, novel spectrum planning schemes for both downlink (DL) and uplink (UL) are proposed. Theoretical analysis and simulation demonstrate that the proposed cellular structure can significantly improve the system capacity in both DL and UL, especially at the cell edge.

The correct evaluation of P2P streaming system models needs the validation in real world system. However, there is lack of systematic and integrated measurement method for real world P2P streaming system. In this paper, we propose a P2P streaming network measurement method based on a peer's buffer occupancy probability. Our method is based on the fixed duration buffer property of commercial P2P streaming systems. We prove the measured buffer occupancy probability reflects the chunk propagation process in the P2P network. We then propose a P2P streaming chunk propagation model and verify it in the commercial P2P streaming network using our measurement method. Our measurement method is useful for measuring and analyzing miscellaneous P2P streaming systems. And our model and parameter estimation are useful for existing P2P simulators to choose correct parameters and are meaningful for researchers to understand the real meaning behind the parameters.

In this paper, we present source management routing algorithm (SMRA) providing a backup routing path for BGP. Each AS has a unique name, and chooses its virtual neighbors by name. Each AS only maintains one routing path to its virtual neighbors, and the ASes along a path to its virtual neighbors keep track of this path. SMRA provides routing paths between arbitrary pairs of ASes only based on the unique name. For this kind of name-based scheme, naming rule is of great importance. This paper makes a detailed analysis of the flat-name assignment policy for SMRA. We focus on two kinds of flat-name assignment policy: one is topology relative, and the other is topology irrelative. On the premise of awareness of network topology, flat-name assignment policy can improve SMRA routing performance.We ran a large number of experiments to explore what factors influence SMRA routing performance. Different flat-name assignment policies have a great impact on SMRA. We find virtual neighbor path length is not the longer the better through the analysis of flat-name assignment policy. Core node is another important factor impacting SMRA routing effectiveness. The result of experiment shows that the flat-name assignment policy that increases the number of virtual neighbor paths passed by core ASes can shorten average SMRA path length.

Autonomous systems (ASes) in the Internet structure are administrated by separate economic entities. They often meet direct or indirect competitions with each other when providing transit services to the same customer that is multihomed to them. In this paper, we explore possible strategies to enhance one's competition strength against other rivals by juggling AS path in routes advertised to neighbors without violating routing safety. Our strategies indicate that a provider can simply shorten or prolong AS path to achieve the aim. Moreover, we propose novel methods to help a provider defeating other competitors even if its routes are assigned lower local preference by its customers. We also evaluate the effectiveness of these strategies on a real Internet topology. It shows valuable use for network operators to get more market share and financial gains from multihomed customers.

In this paper, the throughput performance of the access links (i.e., base station to mobile station and relay station to mobile station) is analyzed for the wireless relay networks based on IEEE 802.16j. An isolation band based frequency reuse scheme (IBFRS) is proposed, which introduces an isolatio

With the wide spread of P2P streaming systems, there appear some hackers who try to pollute the system by inserting fake data chunks into the system. These "dirty" chunks will then be propagated to many normal peers, which will result in the failure of the whole system. Considering the playback qual

With the growth of the popularity of various P2P file-sharing systems, the tussle between ordinary P2P users and copyright protectors becomes more and more fierce. The contests of servers (supernodes), the key components of these systems, have turned to be the focus of the combat. Some copyright pro

Bandwidth allocation, in terms of distributing available data slots among different users, is studied for QoS provisioning in IEEE 802.16 networks. By considering the Automatic Repeat reQuest with Selective Acknowledgement (ARQ-SA) scheme for erroneous wireless channels, a mathematical model is established to theoretically analyze the delay performance of transmitting Service Data Unit (SDU) under a multiuser environment. The analytical results indicate that the delivery delay of the SDU is dominated by the time spent for the first transmission of all its Protocol Data Units (PDUs). Based on this observation, a novel dynamic bandwidth allocation algorithm is proposed and a detailed performance analysis is provided. Simulation results show that the proposed bandwidth allocation algorithm can significantly improve the delay performance of SDUs and ensure the fairness among different users.

Reuse partitioning (RP), a promising technique for constructing high efficient multi-cell OFDM systems, has brought a lot of attentions from both industry and academia. In this paper, by considering the characteristics of various service flows, we first introduce a new performance metric, called flow-satisfaction-degree (FSD), and then formulate an optimization problem for maximizing the FSD over the whole system. We then propose a FSD-based scheduling (FSDS) algorithm for the static RP system. Simulation results demonstrate that the proposed algorithm greatly outperforms the traditional static allocation scheme in terms of FSD and system throughput for the fully loaded system.

BGP may take a long "path exploration" process to converge when a single failure occurs. In this paper, we propose a simple novel mechanism, named anti-loop probing (ALP), to achieve fast BGP convergence. ALP greatly speeds up the "path exploration" process by slightly modifying BGP rules of when to send withdrawals and when to send announcements. Our simulation shows that ALP can achieve a dramatic improvement in BGP convergence and can be implemented with a little memory overhead.

Routing information is so crucial to an operational network that it is always regarded as confidential by network administrators. This paper proposes a novel routing inference method that only needs the knowledge of the network topology and the link counts, both of which can be obtained from MRTG (multi-router traffic grahper) data. The insight is that the traffic observed on each link arises from the superposition of the traffic demands between the origin-destination (OD) pairs and each traffic demand corresponds to a unique path. The method employs expectation maximization (EM) algorithm cooperating with a hypothetic pseudo routing scheme, which is expected to embrace the real routing, to compute a pseudo traffic matrix. The real routing then can be conjectured from this pseudo traffic matrix. This method is applied to a real IP network, and the results show that it correctly infers the routings for 87% OD pairs.

IEEE 802.16, also known as WiMax (worldwide interoperability for microwave access), introduces the automatic repeat request with selective acknowledgement (ARQ-SA) scheme to improve the reliability of the wireless link. For ARQ-SA, packets or protocol data units (PDUs), several of which compose one service data unit (SDU) from the upper layer, are transmitted orderly, but only those negatively acknowledged packets are retransmitted. We analyze the delay performance of SDU under ARQ-SA in a multiuser network environment. Our analysis shows that the SDU delay is mainly determined by the first transmission of all its PDUs. Further more, we propose a simple scheme to reduce the delivery delay of SDU. Simulation results are given to demonstrate the accuracy of the analytical one.

As one of the killing applications in NGI, peer-to-peer networks (P2P for short) have rapidly developed in recent years. We survey and catalog the current hot research aspects in P2P networks, compare and review most of the research work in P2P networks, and summarize the research means and their problems

A novel active queue management scheme for Internet DiffServ named class-guided random early discarding (CGRED) is proposed in this paper. The key enhancement of CGRED to standard RED is to introduce per-class states at routers and compute probability of discarding packets of different traffic classes adaptively based on the periodical measurements of actually consumed bandwidth of each classes, CGRED can maintain the assigned priority and pre-allocated bandwidth for each service class, eliminate the starvation of lower-priority classes, and ensure that each individual flows of a higher-priority class to obtain averaged rate not less than that of lower classes. Simulation results are presented to show that CGRED is simple, robust and scalable to be implemented.

The increasing demand of multimedia applications has spurred recent interest in end-to-end congestion control for real-time applications. However, all these mechanisms proposed so far try to provide smooth sending rate and be friendly to TCP. They have paid little attention to the characteristics that distinguish a real-time application from a non-real-time service. The works on equal and unequal protection multimedia transmission through FEC (forward error correction) encoding show that, there are many different structures in an encoded multimedia stream with different importance in the media restoration. In order to protect these different structures of different importance in the transport layer instead of in application layer through FEC a coupon based AIMD (CAIMD, coupon based additive-increase multiplicative-decrease) algorithm is proposed in this paper. In this algorithm, a coupon is attached to each sending packet to indicate the importance of the message carried in this packet. The network services packets differently according to the coupon value attached on them. In order to make CAIMD TCP friendly, the "linear" increase slope in CAIMD is dynamically changed with the importance of the message carried in a sending packet. Theoretical analysis and simulations carried in this paper show that CAIMD is capable of providing different protection in the packet level with a fine granularity, which opens a new means to optimize the QoS of media streams in network transportation. In additional, CAIMD is friendly to TCP flow as well.

QoS routing has generally been addressed in the context of reservation-based network services (e.g. ATM, IntServ), which require explicit (out of band) signaling of reservation requests and maintenance of per-flow state information. It has been recognized that the processing of per-flow state information poses scalability problems, especially at core routers. To remedy this situation, in this paper we introduce an approach for stateless QoS routing in IP networks that assumes no support for signaling or reservation from the network. Simple heuristics are proposed to identify a low-cost delay-constrained path. These heuristics essentially divide the end-to-end path into at most two "superedges" that are connected by a "relay node". Routers that lie on the same superedge use either the cost metric or the delay metric (but not both) to forward the packet. Simulations are presented to evaluate the cost performance of the proposed approach.

In this paper, we propose a fast multicast routing heuristic, called DCMA, for delay-sensitive applications. The running complexity of DCMA is O(m log m+|V|), where m is the size of the multicast group and |V| is the number of nodes in the network. We first present a unicast version of DCMA, called SDCR, which is used to setup an end-to-end, cost effective delay-constrained path between two nodes. SDCR can always find a delay-constrained path if one exists. Its running complexity is O(|V|). SDCR is used in constructing DCMA, which is guaranteed to be loop free. Simulation results are used to demonstrate the high performance and cost effectiveness of the proposed heuristic.