Search

In reputation-based peer-to-peer systems, reputation is used to build trust between peers and help selecting the right peers to download from. In this paper, we argue that reputation should not be used for service differentiation among the peers. To provide the right incentives for peers to share files and contribute to the system, the new concept of Contribution Behavior is introduced for partially decentralized peer-to-peer systems. Service differentiation is achieved based on the Contribution Behavior of the peers rather than their reputations. Simulation results assess the ability of the proposed algorithm to effectively identify free riders and malicious peers that upload malicious content, hence reducing the level of service provided to these peers and preserving network resources. On the other hand, good peers that contribute to the system receive better services which increases their satisfaction significantly. [ABSTRACT FROM AUTHOR]

This paper presents an open queueing model with blocking that enables us to determine the optimal fraction c* of the uplink channel capacity that should be dedicated to the contention channel in order to minimize the mean response time in a DOCSIS cable network. To assess the performance of this queueing network we make use of a decomposition technique. One of the key components of the model exists in capturing the behavior of the conflict resolution algorithm by means of a single processor sharing queue. The model is validated in three successive steps by means of several simulation programs. We also explore the impact of a variety of systems parameters, e.g., the number of cable modems, the initial backoff window size, etc. , on the optimum c*. Keywords: DOCSIS Cable Networks, contention channel, performance evaluation, queueing networks, decomposition algorithm. [ABSTRACT FROM AUTHOR]

We consider the issue of QoS (Quality of Service) in a network catering to isochronous VoIP (Voice over IP) sessions. Our simulation experiments strongly suggest that the single-path paradigm of implementing network-layer virtual circuits neither yields the best utilization of network resources (buffer space) nor is it able to provide the best end-to-end service in terms of loss rate and delay. Instead, it turns out that the dynamic exploration of alternative paths at the packet level with small buffer spaces at the routers results in a more efficient and economical delivery. Keywords: routing, multiple path routing, deflection, VoIP, QoS. [ABSTRACT FROM AUTHOR]

Estimating the reliability of an end-to-end network path is critically important for applications that support remote real-time task execution. Available bandwidth, which is defined as a minimum spare capacity of links constituting a network path, is an important QoS characteristic of the path. In this work we demonstrate a new approach to modelling available bandwidth behavior from a time-series analysis prospective. In particular, we introduce a notion of crossing probability-the probability that available bandwidth drops below the QoS critical threshold for the period of time required for a real-time task execution.We estimate "crossing probability" by an application of the ARCH2 (AutoRegressive Conditional Heteroscedasticity) model to available bandwidth behavior. We estimate model coefficients β0 and β1 to quickly output "crossing probability" for arbitrary values of threshold and length of the real-time task. The model was evaluated on real bandwidth measurements across multiple network paths. Index terms: Network measurements, Statistics, Stochastic processes. [ABSTRACT FROM AUTHOR]

We study a wavelength assignment maximization problem in multifiber WDM networks. Given a network G, a set of requests, the number of fibers per link and the number of wavelengths, we want to maximize the number of requests that can be satisfied simultaneously. We propose polynomial time algorithms, that are either optimal or have a guaranteed worst case performance in basic topologies, such as chain, ring and star networks. [ABSTRACT FROM AUTHOR]

In this paper, we propose an effective access control scheme in an voice/video/data integrated CDMA system. The proposed scheme schedules the transmission of data traffic during low voice/video traffic density period. In addition, to guarantee the delay requirements of data traffic, the transmission rate control of video traffic is triggered when the access delay of data traffic exceeds delay requirements. Numerical results show that outage probability is decreased by allowing the delay of data traffic and decreasing the transmission rates of video traffic. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel scheme of Hierarchical Eulerian Ring-Oriented Multicast Protocol over mobile ad hoc network. It has features that concentrate on efficiency and robustness simultaneously. It is also an application-driven proposal for hazard detection. Simulation results show different level of improvements on control traffic, end-to-end delay by comparing with tree-based and mesh-based multicast protocols. Keywords: Hierarchical, Eulerian Ring, Multicast, Ad hoc network. [ABSTRACT FROM AUTHOR]

Keywords: Resilient Packet Ring, Differentiated Services, Per Hop Behavior. [ABSTRACT FROM AUTHOR]

In this paper, we explore a novel approach to perform a probabilistic fast analysis of web communications. Instead of relying on pattern matching algorithms, we look at simple network and transport level parameters and try to infer what happens at the application level. Our approach provides the ability to perform a trade-off between analysis speed and precision that could prove useful for some traffic analysis applications. [ABSTRACT FROM AUTHOR]

SCTP is a general purpose transport protocol featuring multi-homing support and flexible, message oriented data delivery services. With respect to multi-homing, the SCTP standard uses this feature for network level redundancy only and, thus, does not provide load sharing capabilities among the redundant links. In order to satisfy the strict performance requirements for signaling transport, efficient load sharing among all active links is desirable in certain scenarios. Therefore, some extensions providing load sharing functionality have been proposed. In this paper, we suggest an improved load sharing algorithm for SCTP with path based selective acknowledgements and present results of a simulation study to demonstrate the benefits of our algorithm. Keywords: SCTP, transport protocol, multi-homing, load sharing. [ABSTRACT FROM AUTHOR]

In this paper, we present an approach to stable and fair mobile ad hoc networks. Our approach targets desired quality features using customizable clustering algorithms. Simulation results show that significant improvement on network stability and fairness can be achieved using our approach. [ABSTRACT FROM AUTHOR]

We propose an auction-based pricing scheme for admission in a GPRS network, that could enhance the GPRS data service. Important features of our approach are the partitioning of dedicated channels for enhanced data service and the employment of an auction mechanism based on revenue-maximizing auctions (optimal auctions). [ABSTRACT FROM AUTHOR]

In large wireless sensor networks, the few nodes close to the monitoring station are likely to prove the bottleneck in the useful lifetime of the network. We examine a strategy of equipping these nodes with a larger share of the total initial energy (battery) than the others, and generalizing this notion to the rest of the network. We solve a design problem involving optimizing the network lifetime using no more than a given number of distinct battery levels, and verify the results from the model by direct simulation. [ABSTRACT FROM AUTHOR]

We propose the so-called backup tree algorithm to compute a set of n-1 backup multicast delivery trees from the default multicast tree for application level multicast. For each backup multicast tree exactly one link of the default multicast tree is replaced by a backup link from the set of available links. The backup tree algorithm calculates the n-1 trees with a complexity of O (m log n). [ABSTRACT FROM AUTHOR]

In this paper, we propose a MAC protocol for a passive optical network (PON) employing wavelength-division multiplexing (WDM) with arrayed-waveguide gratings (AWGs) performing routing functionality at the remote node. In proposed MAC protocol, we employ a Request/Permit based MAC protocol using multipoint control protocol (MPCP). It is simulated using OPNET and their performances are evaluated in terms of bandwidth utilization and queuing delay. [ABSTRACT FROM AUTHOR]

We analyze the performance of an IEEE 802.15.4 compliant network cluster operating in the beacon enabled mode with both downlink and uplink traffic. We investigate the non-saturation regime and outline the conditions under which the network abruptly goes to saturation. The operation of the WPAN is modeled through discrete time Markov chains and the theory of M/G/1 queues. The model considers acknowledged transmissions and includes the impact of different network and traffic parameters such as the packet arrival rate, packet size, inactive period between the beacons, and the number of stations. We analyze the stability of the network queues and show that the stability of the downlink queue at the coordinator is the most critical for network operation. [ABSTRACT FROM AUTHOR]

Distributed clustering techniques are considered effective and practical for power-saving in Wireless Sensor Networks (WSNs). In this paper, we propose a novel cluster formation scheme in WSNs, called StepWise AdapTive Clustering Hierarchy (SWATCH). SWATCH aims to solve the ClusterHead (CH) number uncertainty problem common to existing distributed clustering schemes, while keeping the desirable properties of self-organization, simplicity and dynamic adaptation. We develop a two-tier hierarchical Markov chain model to track the operation of SWATCH. Based on this model, we derive formulations of the statistical properties of our proposed scheme. Numerical results verify the design objectives in that the number of selected clusterheads highly conforms to the optimal value. [ABSTRACT FROM AUTHOR]

We propose a Node Cooperative Automatic Repeat reQuest (ARQ) scheme for wireless ad-hoc networks to combat the effects of channel fading on the performance of link layer retransmission scheme. The proposed scheme is inspired by the idea of cooperative diversity. Simulation results are given to demonstrate the significant throughput gain, even when the quality of channel between the communicating nodes is poor. [ABSTRACT FROM AUTHOR]

In real-time Internet based teleoperation systems, the operator controls the robot and receives feedback through the Internet. Supermedia refers to robotic control commands, video, audio, haptic feedback, and other sensory information in the control system. Traditional transport services may not be able to meet the timely transmission requirements and dynamic priority changes of supermedia streams. Supermedia TRansport for teleoperations over Overlay Networks (STRON) uses multiple disjoint paths and forward error correction encodings to reduce end-to-end latency for supermedia streams. Network routes and encoding redundancy may be adjusted dynamically to meet the supermedia QoS requirements. NS2 simulations and evaluations using available bandwidth traces from globally distributed computing nodes show that STRON can significantly reduce latency compared with available transport services. keywords: Teleoperation, Overlay networks, Forward error correction. [ABSTRACT FROM AUTHOR]

We present a simple and fast distributed algorithm for Bluetooth network formation. Our algorithm requires no knowledge on the underlying physical topology, and proceeds in only one phase to connect the devices. If the physical topology is weakly connected, then the algorithm guarantees that the resulting network will be connected with high probability. The algorithm is also symmetric in the sense that each device executes exactly the same algorithm, thereby increasing the flexibility of network deployment. In contrast, previous results (e.g.,[6,3,2,5,10,1,8,9,4]on Bluetooth network formation require the underlying physical topology to be a complete graph, nodes to be asymmetric, or proceed in more than one phase to connect disconnect components constructed in the first phase. [ABSTRACT FROM AUTHOR]

Some of the main reasons which prevents the deployment of IP multicast are forwarding state scalability and control explosion problems. In this paper, we propose an algorithm called Q-STA (QoS Scalable Tree Aggregation) which reduces the number of forwarding states by allowing several groups to share the same tree. Q-STA accepts groups only if there is enough available bandwidth. Q-STA accepts much more groups and performs faster aggregations than previous algorithms. [ABSTRACT FROM AUTHOR]

Mobile IP has been developed to give mobile nodes freedom to move to new locations away from home networks. However, Mobile IPv4 requires the implementation of address binding on all IPv4 hosts, i.e., modification, to prevent the long delay due to the triangular routing problem. The host modification is a huge hindrance to the deployment of mobility support. Meanwhile, a new scalable interoperability architecture called UNA (Universal Network Adaptation), which helps the Internet smoothly evolve to MTI (Multi-Tier Internet) or permits easy deployment of a new network technology, was presented. In this paper, we extend UNA, so that we can move the point of address binding from IPv4 hosts to UNA gateways. Therefore, mobility support with no triangular routing problem can be achieved in MTI, without host modification. [ABSTRACT FROM AUTHOR]

In this paper we present a flexible architecture providing a communication platform between heterogeneous components for inter-domain QoS and traffic analysis in large-scale, multi-domain Internet infrastructures. [ABSTRACT FROM AUTHOR]

We propose a notion of extended dominating set whereby each node in an ad hoc network is covered by either a dominating neighbor or several 2-hop dominating neighbors. This work is motivated by cooperative communication in ad hoc networks where transmitting independent copies of a packet generates diversity and combats the effects of fading. In this paper we propose several efficient heuristic algorithms for constructing a small extended dominating set. [ABSTRACT FROM AUTHOR]

Proportional delay differentiation (PDD) aims to maintain pre-specified packet queueing-delay ratios between different classes of traffic at each hop. Existing rate-allocation approaches for PDD services assume the average queueing delay of a class is inversely proportional to its service rate. This assumption may not be valid in a non-heavily loaded system. In this paper, we present a rule-based approach to provide consistent PDD services under various load conditions. In this approach, the service rate of a class is adjusted according to a set of control rules. Simulation results demonstrate that, in comparison with other rate-allocation approaches, the rule-based approach is able to provide PDD services under light, moderate, and heavy load conditions consistently. [ABSTRACT FROM AUTHOR]

Proxy caching is a key technique to reduce transmission cost for on-demand multimedia streaming. However, its effectiveness is limited by the insufficient storage space and weak cooperations among proxies and their clients. In this paper, we propose COPACC, a novel cooperative proxy-and-client caching system that combines the advantages of both proxy caching and peer-to-peer (P2P) client communications. We propose a comprehensive suite of protocols to facilitate the interactions among different network entities in COPACC. We also develop an efficient cache allocation algorithm to minimize the aggregated transmission cost of the whole system. Simulation results demonstrate that COPACC achieves remarkably lower transmission cost. Moreover, it is much more robust than a pure P2P system in the presence of node failures. [ABSTRACT FROM AUTHOR]

We propose a novel call admission control scheme to support the multiservice of cellular networks particularly under heavy loaded cell condition. The key idea of our strategy is that the services which underutilize their assigned bandwidth because of their think time are dynamically grouped and forced to share the bandwidth in round robin especially when the resource availability is unfavorable. We present the simulation results that show our proposed scheme outperforms a conventional bandwidth reconfiguration strategy in terms of call blocking probabilities. [ABSTRACT FROM AUTHOR]

High speed networks are highly dynamical systems. Large deviation techniques have been employed to characterize their loss probability. Large deviation is also used to calculate shadow prices of quality of service of a scalable network queue with respect to buffer size B, capacity C and arrival rate N.In this paper we prove that these shadow prices are independent of (B,C,N) parameters. Gibbs Duhem law of thermodynamics is described. Equivalent Gibbs Duhem type law in scalable network queue is derived. Application of equivalent network Gibbs Duhem law is discussed. Index Terms: Quality of Service, Macroscopic parameter, Microscopic Parameter, Gibbs Duhem law. [ABSTRACT FROM AUTHOR]

We describe a problem of redundant flooding induced by multiple sensor nodes during route discovery in event-driven wireless sensor networks, and propose a novel extension to the on-demand ad hoc routing protocol, in order to reduce the number of signaling messages during the route discovery phase. That is, our extension reduces energy consumption during route discovery. The heuristically and temporarily selected Path Set-up Coordinator (PSC) plays the role of a route request broker that alleviates redundant route request flooding. The simulation results show that our extension not only helps to conserve energy, but also reduces the disruption caused by the broadcast storm. [ABSTRACT FROM AUTHOR]

Most routing protocols employ address aggregation to achieve scalability with respect to routing table size. But often, as networks grow in size and complexity, address aggregation fails. Other networks, e.g. sensor-actuator networks or ad-hoc networks, that are characterized by "organic growth" might not at all follow the classical hierarchical structures that are required for aggregation. In this paper, we present a fully self-organizing routing scheme that is able to efficiently route messages in random networks with randomly assigned node addresses. The protocol combines peer-to-peer techniques with source routing and can be implemented to work with very limited resource demands. With the help of simulations we show that it nevertheless quickly converges into a globally consistent state and achieves a routing stretch of only 1.2 - 1.3 in a network with more than 105 randomly assigned nodes. Keywords: Self-organization, Peer-to-Peer, Ad-Hoc Routing. [ABSTRACT FROM AUTHOR]

In this paper we propose a Medium Access Control (MAC) protocol for the efficient integration of high quality video traffic with ftp data packet traffic over a wireless channel of very high capacity. Via an extensive simulation study, we evaluate the system's performance under a variety of possible loads which consist of actual MPEG-4 streams and ftp sessions. [ABSTRACT FROM AUTHOR]

We propose the use of an improved Internet coordinate system to allow multihomed IPv6 sites to select the source and destination address pair that provides a low delay path. We describe the new coordinate system and evaluate its use on the RIPE test box data set. [ABSTRACT FROM AUTHOR]

We present here the results of the measurements of rain-induced attenuation in the vertically polarized signal propagating at 12.25GHz during some rain events, which occurred in the rainy season of the year 2001 at Yong-in, Korea. The attenuation measured experimentally was compared with that obtained using the International Telecommunication Union Radio Communication Sector (ITU-R) model, the SAM model and the Global model. Our measured results are in good agreement with the ITU-R prediction. [ABSTRACT FROM AUTHOR]

This paper proposes a framework called Virtual Multi-Homing (VMH) to achieve loose source-based path selection and improve inter-domain path diversity. VMH is based on the concept of Virtual Peering and Multi-Homing Overlay to set up flexible inter-domain relationships. By interacting with BGP whenever possible, VMH can achieve scalable inter-domain route discovery without introducing duplicate work. In addition, VMH is a complementary approach to the existing Internet routing infrastructure and can be incrementally deployed. [ABSTRACT FROM AUTHOR]

We analyze the performance of 802.11 WLANs that employ the Distributed Coordination Function (DCF). We consider contending stations within radio proximity, and investigate the case in which stations operate under non-saturated conditions. Our modelling technique can be used to study several important issues in 802.11 networks, such as the impact of bursty traffic and the system performance in a multirate environment. The accuracy of the analytical results is verified by simulation with ns-2. [ABSTRACT FROM AUTHOR]

The requirements on IP routers continue to increase, both from the control plane and the forwarding plane perspectives. To improve scalability, flexibility, and availability new ways to build future routers need to be investigated. This paper suggests a decentralized, modular system design for routers, based on control elements for functionalities like routing, and forwarding elements for packet processing. Further, we present measurements on the distribution of large routing tables in an experimental platform consisting of one control element and up to 16 forwarding elements. [ABSTRACT FROM AUTHOR]

Studies have shown that the Internet has experienced the widespread failures such as router crash, fiber cut, or scheduled maintenance. Ideally, routing protocols should be able to quickly find alternate paths to reroute around failures. In this paper, we consider one important factor that prevents routing protocols from achieving this goal: the delay of finding and obtaining alternate paths, defined as routing lag. We show that a significant number of routing failures in the Internet are caused by routing lags, and they can last for a significant period of time. [ABSTRACT FROM AUTHOR]

Recent findings have revealed that the carrier-sensing range set in current major implementations does not detect all interference signals in 802.11 networks. In this paper, we investigate the effect of interference and develop a mathematical model for it. The accuracy of our model is verified via simulations. Based on an insight from our model, we present a simple protocol that operates on the top of 802.11 MAC layer and achieves more throughput than rate-adjustment schemes. [ABSTRACT FROM AUTHOR]

This paper presents Media- and TCP-Friendly Rate Control Algorithm (i.e. MTFRC) for scalable video streams. We develop a two-timescale approach to satisfy media friendliness in the short-term, while maintaining TCP friendliness in the long-term. We evaluate MTFRC with five criteria, namely TCP-fairness, responsiveness, aggressiveness, video quality and smoothness of sending rate. Our simulation results manifest that MTFRC outperforms the TCP-Friendly Rate Control Protocol (TFRC) and improves the overall video quality. [ABSTRACT FROM AUTHOR]

This paper extends the Birkhoff-von Neumann unicast switching strategy to the multicast case. Using a graph theoretic model we show that the rate region for a traffic pattern is precisely the stable set polytope of the pattern's ‘conflict graph', in the no-fanout splitting case. Computing the offline schedule is equivalent to fractional weighted graph coloring which takes polynomial time for perfect graphs. For a general conflict graph, we show that deciding achievability of a given rate vector is NP-hard, but can be done in polynomial time for the case of moderate multicast load. The result naturally leads to an offline schedule. [ABSTRACT FROM AUTHOR]

Call admission control is a key element for providing quality of service (QoS) in mobile wireless networks. Traditional admission control schemes only address call-level QoS guarantee because of the underlying circuit-based network architecture. In contrast, emerging wireless technologies such as 3G and 4G tend to be packet-switched rather than circuit-switched because the packet-based architecture allows better sharing of the scarce wireless resources. This paper introduces a novel distributed call admission control scheme called PFG, which maximizes the wireless channel utilization subject to a predetermined bound on the call dropping and packet loss probabilities for variable-bit-rate traffic in a packet-switched wireless cellular network. In particular, we show that in wireless packet networks, the undesired event of dropping an ongoing call can be completely eliminated without sacrificing the bandwidth utilization. Extensive simulation results show that our scheme satisfies the hard constraint on call dropping and packet loss probabilities while maintaining a high bandwidth utilization. [ABSTRACT FROM AUTHOR]

The emerging heterogeneous networking environment will comprise diverse link layer technologies like 3G, WLANs and WPANs. In this context, multimedia applications should be able to cope with packet losses and delays due to congestion, wireless transmission errors and vertical handovers. This paper addresses the functional requirements from an advanced adaptation architecture, which incorporates enhanced end-to-end adaptation schemes that exploit information delivered by the next-generation terminal. The terminal's management entity should provide information at least for the local access network condition, e.g. estimates of the available bandwidth and wireless link losses, and handover notifications. The adaptation architecture does not count on the existence of QoS infrastructure; however, exploitation of such infrastructure is possible through the collaboration between the terminal and a network management entity. We have extended the LDA and TFRC rate adaptations algorithms to make use of the enhanced functionality. Through simulations we validate the robustness of these extended schemes against vertical handovers. Keywords:Rate adaptation, Vertical handover, LDA, TFRC [ABSTRACT FROM AUTHOR]

Providing multimedia services with Quality of Service (QoS) guarantees in next generation wireless cellular networks poses great challenges due to the scarce radio bandwidth. Effective Call Admission Control (CAC) is important for the efficient utilization of the limited bandwidth. In this paper, the design of CAC for a decision-based Markovian model of multimedia wireless networks is considered. We propose an optimal CAC policy that aims at maximizing the system utilization while stratifying the QoS constraints bounding the handoff dropping probability of each traffic class. We used the Semi-Markov Decision Process (SMDP) technique to represent the proposed CAC. The optimal CAC decisions for each state are found by solving the linear programming formulation problem. Numerical and Simulation results show that the system upholds the handoff call dropping probability required by each traffic class while maximizing revenue for service providers. The requirements of the mobile users are hence satisfied in periods with different loads, including overload. Moreover, the implemented policy ensures efficient utilization of resources. This latter facet is highly desirable by service providers. [ABSTRACT FROM AUTHOR]

In 3G cellular networks, high data-rates can be achieved. However, fundamental capacity limitation still exists. Call requests are frequently blocked in hotspot areas. Load balancing among cells helps to solve this problem and to utilize the radio resources. However, existing load balancing schemes are not designed specifically for 3G networks. Some schemes are not flexible enough or even practical for such networks. In this paper, we propose a novel load balancing and relaying framework for 3G TDD W-CDMA multi-hop cellular networks. This framework consists of a load balancing scheme called ALBA, a routing scheme called ACAR and a slot assignment scheme called E-DSSA. Our framework provides a realistic integrated load balancing solution for these networks. Simulation results show that this framework reduces the call blocking ratios of hotspot areas, balances load among cells and increases system throughput with low packet delay. [ABSTRACT FROM AUTHOR]

The current IEEE 802.16a and 802.16d standards of wireless metropolitan area networks specify a ranging channel in the OFDMA physical layer that employs a set of CDMA codes for ranging and bandwidth requests. The ranging channel is contention-based and inherently unstable. In this paper, we propose two stabilization algorithms to enable efficient utilization of the ranging channel at close to the theoretical throughput limit, and analyze their performance using a continuous time Markov chain M/M/1 model. We show how to estimate system parameters such as the number of backlogged users, arrival rate and the first exit time for the critical. Based on these parameters, we present two methods for channel stabilization, for the cases that the number of ranging codes per frame is fixed and adjusted dynamically, respectively. We then present simulation results to show that, by restricting the actual arrival rate or dynamically adjusting the number of ranging codes, the ranging channel can be stabilized under all traffic conditions. Keywords: Wireless metropolitan area network (WMAN), OFDMA, CDMA, Ranging channel, Ranging code, System stability. [ABSTRACT FROM AUTHOR]

Most of previous study of radio resource allocation in traditional wireless networks concentrates on network layer connection blocking probability QoS. In this paper, we show that physical layer techniques and QoS have significant impact on network layer QoS. We define a novel concept of cross-layer effective bandwidth and use this to measure the unified radio resource usage taking into account both physical layer linear minimum-mean square error (LMMSE) receivers and varying statistical characteristics of the packet traffic in code devision multiple access (CDMA) networks. We demonstrate the similarity between traditional circuit-switched networks and packet CDMA networks, which enables rich theories developed in traditional wireless networks to be used in packet CDMA networks. Moreover, since both physical layer signal-to-interference ratio (SIR) QoS and network layer connection blocking probability QoS are considered simultaneously, we can explore the tradeoff between physical layer QoS and network layer QoS in packet CDMA networks. [ABSTRACT FROM AUTHOR]

Packet-based optical access ring is becoming a promising solution in metropolitan networks. Its performance depends mainly on how optical resource sharing takes place among the different competing access nodes. In such a network fairness issues are likely to arise between upstream and downstream nodes competing to access a common data channel. This paper provides a new protocol called TCARD (Traffic Control Architecture using Remote Descriptors), based on a preventive reservation scheme, to alleviate the fairness problems. The reservation process consists in forcing the upstream nodes to ensure enough available bandwidth for downstream nodes' transmission purpose. Moreover, we develop analytical models in order to assess the access delay when TCARD is enabled. The analytical and simulation results show how the proposed solution alleviates the performance degradation and the resource sub-utilization while achieving fairness among bus nodes. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel approach, stealth multicast, which offers a practical solution for the adoption of network-level IP multicast. Rather than focusing on a global scale such as with previous approaches, stealth multicast optimizes efficiency on a domain-wise scale. In short, stealth multicast dynamically combines redundant data payloads into virtual groups for multicast transmission across the domain. At the edge of the domain, the packets are converted back to unicast, thus keeping stealth multicast true to its namesake in that neither the user applications nor the external domain are aware of the presence of multicast. We present simulation studies to show the potential of stealth multicast. [ABSTRACT FROM AUTHOR]

The main goal of this work is to provide bandwidth allocation that is robust against the behavior of greedy or malicious users. The traditional solution, Fair Queueing, allocates capacity per sourcedestination pair in accordance with the max-min fairness criterion. While Fair Queueing, defined as above, has been successful and popular to a large extent, it does not prevent greedy or malicious users from getting unfair shares of capacity. In particular, it is vulnerable to end-points simply establishing multiple parallel connections to increase their allocated capacity. In order to overcome this limitation, we propose Justice, which allows for robust, yet flexible bandwidth allocation in the Internet. Justice employs weighted per source bandwidth allocation to accommodate traffic sources with varying bandwidth requirements. We describe an efficient and scalable mechanism for determining, for each source s, the weight φk(s) at any given link k. We demonstrate through analysis and simulation that Justice is flexible, efficient, scalable, and robust to all identified attacks related to bandwidth allocation. Keywords: Bandwidth Allocation, Per-Source Weighted Fairness. [ABSTRACT FROM AUTHOR]

We consider a single cell of a multi-service CDMA network, in which some of the service classes are explicit rate controlled. We call these elastic service classes. The instantaneous bit rate of elastic services is dynamically adjusted between a minimum and maximum value such that the system always remains work conserving. We develop a Markov model that allows us to study the impact of such state dependent (dynamic) rate control on the class-wise blocking probabilities and the first two moments of the holding times. We conclude that dynamic (state dependent) rate adjustment decreases the class-wise blocking probabilities and only moderately increases the expectation and the second moment of the time spent in the system. [ABSTRACT FROM AUTHOR]