Studies on large scale reliable multicast based on active network

Large, distributed simulations where multicast is used for data, distribution has an inherent scalability problem-the number of multicast groups grows rapidly with the number of participants. We describe a publish/subscribe based active networking system where receiver interest information is stored as packet filters at the active nodes on the multicast distribution tree and multicast data is pruned at the earliest node possible. Modifications to the system provide reliable data delivery to support loss-sensitive data stream. Selective caching at some active nodes allows the recipient of a lossy data stream to partially trace back to the first cached instance of the missing packet. We argue that the performance penalty for applications that do not use the active filtering service is minimal, enabling the system to coexist in an open network with other applications.

In this paper we examine the impact of widely spread multicast groups on the performance of reliable multicast protocols. In a brief analysis we show that transmission cost for reliable multicast increases rapidly with the distance between retransmitting and receiving hosts. Since this distance is not considered by existing protocols, which are based on retransmissions originated at the sender or receiver, the performance often is rather poor and a new error recovery concept has to be developed. Our approach. the Scalable and Reliable Multicast Transport protocol (SRMT), allows retransmissions by extended multicast routers to limit the path length for error recovery. Moreover, the retransmission load can be further reduced by an XOR combination of packets. SRMT is defined as an overlay network model and therefore can be applied to any existing multicast protocol.

Multicasting plays an important role in internet networks. Supporting wavelength division multiplexed (WDM) multicasting in an IP over WDM network poses interesting problems because some WDM switches may be incapable of switching an incoming signal to more than one output interface. Although some multicast applications, such as audio/video conferencing can tolerate packet error or loss, other applications such as one-to-many file transfer and military applications do not. Hence, an inevitable need for reliable multicasting arises. The reliable multicast protocol ensures the eventual delivery of multicast data to all multicast group members. The reliable multicast is receiver initiated NACK-based and it makes use of feedback suppression in order to avoid NACK and retransmission implosion. The loss recovery burden is distributed over the multicast group members in order to reduce recovery latency and end-to-end delay. The proposed protocol is evaluated in terms of performance metrics for an IP/WDM optical network which will be the candidate for the next generation internet networks.

Multicast in wireless sensor networks (WSNs) is an efficient way to spread the same data to multiple sensor nodes. It becomes more effective due to the broadcast nature of wireless link, where a message transmitted from one source is inherently received by all one-hop receivers, and therefore, there is no need to transmit the message one by one. Reliable multicast in WSNs is desirable for critical tasks like code updation and query based data collection. The erroneous nature of wireless medium coupled with limited resource of sensor nodes, makes the design of reliable multicast protocol a challenging task. In this work, we propose a time division multiple access (TDMA) based energy aware media access and control (TEA-MAC) protocol for reliable multicast in WSNs. The TDMA eliminates collisions, overhearing and idle listening, which are the main sources of reliability degradation and energy consumption. Furthermore, the proposed protocol is parametric in the sense that it can be used to trade-off reliability with energy and delay as per the requirement of the underlying applications. The performance of TEA-MAC has been evaluated by simulating it using Castalia network simulator. Simulation results show that TEA-MAC is able to considerably improve the performance of multicast communication in WSNs.

Active networks are a promising way to develop new services for data transport, but active routers could also store "on the fly" streams of data for high level services such as Web cache and reliable multicast. In this paper we describe the merging of active networking with distributed storage solutions. We focus our approach on two dedicated frameworks : the IBP suite and the Tamanoir execution environment. We describe the overall architecture of the Active Logistical Storage suite and present first experimental results.

Forward error correction (FEC) has been proposed as a technique for implementing efficient reliable multicast (RM). However, FEC incurs costs in encode/decode delay and implementation complexity. How much benefit is provided relative to these costs and how dependent is the benefit on the specific RM protocol? In this paper, we evaluate the benefits of FEC for RM, considering both proactive and reactive use with three RM recovery techniques: duplicate avoidance, limited scope multicast and subcast. Our simulation-based results indicate that FEC provides little benefit for an efficient RM protocol like OTERS and introduces extra delay for multi-point streaming data applications.

Reliable multicast in wireless ad hoc networks is important for the applications such as distributed computing, chat, and whiteboard. Due to the wireless channel characteristics, obtaining the reliability in multicast packet transmission is a difficult and challenging task. Even though IEEE 802.11 is widely adopted medium access control (MAC) protocol in wireless ad hoc networks, it does not support reliable multicast. Thus, several MAC layer protocols have been proposed that can provide reliable multicast. In this paper, we propose the reliable multicast MAC protocol which is based on the orthogonal frequency division multiple access (OFDMA) systems. The proposed method reduces the overhead required for control packets. Analysis results validate the reliability and efficiency of our multicast MAC protocol.KeywordsMedium Access ControlMedium Access Control ProtocolPacket DelayControl PacketOrthogonal Frequency Division Multiple AccessThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Local loss recovery for reliable multicast can provide significant performance improvement in terms of loss recovery latency, bandwidth consumption and network throughput. Active reliable multicast (ARM) is a novel loss recovery scheme for large-scale reliable multicast. When sufficient active resources of active routers (ARs) and associated cache are available, ARM gives good loss recovery latency performance. The authors build an analytical model for studying the optimal active resource allocation for ARM. They propose a top-down layering analysis (TDLA) approach to derive the expected loss recovery latency (ELRL). For a given multicast tree, the ELRL is derived as a function of the active resource allocation pattern. Simulation experiments reveal that high performance gains can be attained with limited active resources, which are properly allocated. It is also shown that simulation results have a good match with the analytical results. The analytical framework developed can be used for further investigation of various active resource allocation schemes and caching policies.

Tree-based reliable multicast protocols are well-known for being scalable for one-to-many sessions, but their behaviour in terms of throughput and bandwidth requirements has not been identifed for many-to-many sessions. In this paper, existing tree-based reliable multicast protocols are categorised into four classes according to their feedback/retransmission mechanisms. Analysing and comparing them using a new spatial multicast loss model that considers the correlation of packet loss events can yield realistic analysis results. The analysis reveals that for many-to-many sessions, tree-based protocols with unicast NACK, unicast retransmission, and periodic polling are most scalable with respect to throughput and network bandwidth for practical session sizes. The result is contrary to the one-to-many case and it is shown that the reason is that reducing the sender's processing time is a key factor for scaling one-to-many reliable multicast, whereas reducing the receiver's processing time is far more important factor for scalability of many-to-many reliable multicasts.

A reliable multicast protocol enables a process to multicast a message to a group of processes in a way that ensures that all honest destination-group members receive the same message, even if some group members and the multicast initiator are maliciously faulty. Reliable multicast has been shown to be useful for building multiparty cryptographic protocols and secure distributed services. We present a high-throughput reliable multicast protocol that tolerates the malicious behavior of up to fewer than one-third of the group members. Our protocol achieves high-throughput using a novel technique for chaining multicasts, whereby the cost of ensuring agreement on each multicast message is amortized over many multicasts. This is coupled with a novel flow-control mechanism that yields low multicast latency.

This paper introduces a reliable multicast transport protocol RCCMP (reliable congestion controlled multicast protocol) that has been designed to be simple, scalable, reliable and TCP-friendly. The congestion control is a central part of the protocol, where the feedback of the worst receiver is used to control a transmission window in a TCP-like fashion. The scalability issue is addressed with an exponential timers scheme, that is also used to estimate the number of receivers involved in the communication. The protocol neither needs support from network elements nor maintains state information dependent of the number of receivers. The paper presents a number of simulation results on its performance. Besides, some design choices are evaluated.

This paper presents the main concepts of the IST Project FAIN “Future Active IP Networks” [10], a three-year collaborative research project, whose main task is to develop and validate an open, flexible, programmable and dependable network architecture based on a novel active node approach. This generic architecture for active networks is an innovative integration of active networking, distributed object and mobile agent technology. Starting from the definition of a business model that underlines the FAIN architecture, we identify three key working areas for contribution: the active node platform layer, the service programming environment and a built-in management system. The active node platform layer of the FAIN Active Node is comprised of the kernel Operating System, a node resource access control framework, and active components for management, security and service provision. These elements provide the foundations for Execution Environments so that they can operate in an independent manner. A novel service programming environment is envisaged to enable the dynamic creation or update and to secure deployment and operation of protocols. Such an environment supports various role-specific ways of deployment, e.g. application-specific signalling or operator-governed network control signalling.KeywordsActive NetworkMobile AgentActive NodeExecution EnvironmentEnterprise ModelThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

To reduce or eliminate the implosion of acknowledgments at the source of a very large multicast group, current reliable multicast protocols either organize the receivers of a group into a tree or ring, or implement negative acknowledgment (NAK) avoidance algorithms based on random timers. All of these approaches have their limitations and advantages. We present a ring-based reliable multicast protocol, called the evenly-loaded ring protocol (ELRP) which removes processing bursts from nodes in the ring. ELRP achieves throughputs as good as those obtained with tree-based protocols and better than those of receiver-initiated protocols with NAK avoidance. We propose a deterministic NAK avoidance (DNKA) algorithm based on ELRP that performs better than the random NAK avoidance scheme (RNKA). Because tree structures are better suited than rings for wide areas involving paths with long delays, we propose the hybrid reliable multicast protocol (HRMP) which organizes receivers into a backbone acknowledgement tree that connects local areas. Any tree-based protocol with positive acknowledgement can be run in the backbone acknowledgement tree, and ELRP is run in the local areas. The maximum achievable throughput in HRMP is analyzed, which shows that it is completely scalable. The delay of DNKA and RNKA schemes are also analyzed which shows that compared with RNKA, DNKA reduces the retransmission delay significantly.

This paper presents a case study in implementing a moderately complex, useful service on an active network platform. The active application is reliable multicast with congestion control; the platform comprises the Bowman Node Operating System and the Composable Active Network Elements (CANEs) Execution Environment. The importance of the work stems from the lessons it provides about the design and implementation of active platforms in general and Bowman/CANEs in particular. For example, our experience shows that timer-driven active node processing is as important as packet-arrival-driven processing. Thus, execution environments cannot focus exclusively on forwarding, but must also provide efficient timers and allow timer handlers the same capabilities as packet-driven computations. Other areas in which the implementation provides insight include service decomposition approaches for active applications and information sharing among service components.

As the use of IP multicast sessions becomes widespread, the potential benefits derived from currently unavailable topological information on multicast distribution trees may become increasingly critical. We propose a framework for discovering the topology of shared multicast trees based on a novel fan-out decrement mechanism analogous to time-to-live (TTL) decrementing in IP. We propose an algorithm for topology discovery based on the matrix of path/fan-out distances among a set of E session members-the algorithm's computational complexity is O(|E|/sup 2/). We exhibit sufficient conditions for topology discovery based on a reduced distance matrix, and propose a practical protocol to acquire this information requiring the exchange of 2|E| multicast messages of size O(|E|). Finally, we show how the same approach permits nodes to discover the multicast distribution tree associated with members within their fan-out/TTL scoped neighborhoods. This permits one to reduce the computational costs while making the communication costs proportional to the size of neighborhoods.