Mohamed Ould-Khaoua

A performance model for Duato's fully adaptive routing algorithm in k-ary n-cubes

Analytical models of deterministic routing in wormhole-routed k-ary n-cubes have widely been reported in the literature. Although many fully adaptive routing algorithms have been proposed to overcome the performance limitations of deterministic routing, there have been hardly any studies that describe analytical models for these algorithms. This paper proposes a new analytical model for obtaining latency measures in high-radix k-ary n-cubes with fully adaptive routing, based on Duatos algorithm (1998). The validity of the model is demonstrated by comparing analytical results with those obtained through simulation experiments.

Performance Analysis of MANET Routing Protocols in the Presence of Self-Similar Traffic

A number of measurement studies have convincingly demonstrated that network traffic can exhibit a noticeable self-similar nature, which has a considerable impact on queuing performance. However, many routing protocols developed for MANETs over the past few years have been primarily designed and analyzed under the assumptions of either CBR or Poisson traffic models, which are inherently unable to capture traffic self-similarity. It is crucial to re-examine the performance properties of MANETs in the context of more realistic traffic models before practical implementation show their potential performance limitations. In an effort towards this end, this paper evaluates the performance of three well-known and widely investigated MANET routing protocols, notably DSR, AODV and OLSR, in the presence of the bursty self-similar traffic. Different performance aspects are investigated including, delivery ratio, routing overhead, throughput and end-to-end delay. Our simulation results indicate that DSR routing protocol performs well with bursty traffic models compared to AODV and OLSR in terms of delivery ratio, throughput and end-to-end delay. On the other hand, OLSR performed poorly in the presence of self-similar traffic at high mobility especially in terms of data packet delivery ratio, routing overhead and delay. As for AODV routing protocol, the results show an average performance, yet a remarkably low and stable end-to-end delay

A performance model for wormhole-switched interconnection networks under self-similar traffic

Many recent studies have convincingly demonstrated that network traffic exhibits a noticeable self-similar nature, which has a considerable impact on queuing performance. However, the networks used in current multicomputers have been primarily designed and analyzed under the assumption of the traditional Poisson arrival process, which is inherently unable to capture traffic self-similarity. Consequently, it is crucial to reexamine the performance properties of multicomputer networks in the context of more realistic traffic models before practical implementations show their potential faults. In an effort toward this end, we propose the first analytical model for wormhole-switched k-ary n-cubes in the presence of self-similar traffic. Simulation experiments demonstrate that the proposed model exhibits a good degree of accuracy for various system sizes and under different operating conditions. The analytical model is then used to investigate the implications of traffic self-similarity on network performance. We reveal that the network suffers considerable performance degradation when subjected to self-similar traffic, stressing the great need for improving network performance to ensure efficient support for this type of traffic.

Analysis of fully adaptive wormhole routing in tori

Abstract A model of adaptive routing in the hypercube has recently been proposed (Y. Boura, C.R. Das, T.M. Jacob, A performance model for adaptive routing in hypercubes, in: Proceedings of the International Workshop on Parallel Processing, 1994, pp. 11–16). Modelling adaptive routing in a high-radix k -ary n -cube, e.g., the torus, is more complicated than in the hypercube since a message in the former may cross more than one channel along a given dimension. This paper proposes a queuing model of adaptive routing in the torus. The validity of the model is demonstrated by comparing analytical results with those obtained through simulations.

Probabilistic counter-based route discovery for mobile ad hoc networks

Conventional on-demand route discovery for ad hoc routing protocols extensively use simple flooding, which could potentially lead to high channel contention, causing redundant retransmissions and thus excessive packet collisions in the network. This phenomenon has been shown to greatly increase the network communication overhead and end to end delay. This paper proposes a new probabilistic counter-based method that can significantly reduce the number of RREQ packets transmitted during route discovery operation. Our simulation results reveal that equipping AODV routing protocol with the proposed probabilistic counter-based route discovery method can result in significant performance improvements in terms of routing overhead, MAC collisions and end-to-end delay while still achieving a good throughput.

Adjusted probabilistic route discovery in mobile ad hoc networks

Conventional on-demand route discovery methods in mobile ad hoc networks (MANET) employ simple flooding method, where a mobile node blindly rebroadcasts received route request (RREQ) packets until a route to a particular destination is established. This can potentially lead to high channel contention, causing redundant retransmissions and thus excessive packet collisions in the network. This paper proposed two new probabilistic methods that can significantly reduce the number of RREQ packets transmitted during route discovery operation. Our simulation analysis reveals that equipping AODV with an appropriate probabilistic route discovery method can result in significant performance improvements in terms of routing overhead, MAC collisions and end-to-end delay while still achieving a good throughput when compared with the traditional AODV.

Message latency in the 2-dimensional mesh with wormhole routing

Abstract Analytical models of deterministic routing in hypercubes and tori with wormhole routing have been widely reported in the literature. Greenberg and Guan (in R. Greenberg, L. Guan, Modelling and comparison of wormhole routed mesh and torus networks, Proc. 9th IASTED Int. Conf. Parallel and Distributed Computing and Systems, October 1997) have recently described a model of deterministic routing in the 2-dimensional mesh, which has been one of the most popular multicomputer networks. Although there have been many adaptive routing algorithms proposed for this network, there has been hardly any study that proposes an analytical model for these algorithms. This paper proposes an approximate analytical model to compute message latency in the mesh with fully-adaptive routing. Results from simulation experiments are then presented to validate the model.

Dynamic probabilistic counter-based broadcasting in mobile ad hoc networks

In Mobile Ad hoc Network (MANETs), flooding is the simplest broadcasting mechanism where each node retransmits every uniquely received packet exactly once. Despite its simplicity it could potentially leads to high redundant retransmissions causing high channel contention and thus excessive packet collisions in the network. This phenomenon referred to as broadcast storm problem has been shown to greatly increase the network communication overhead and end-to-end delay. Numerous probabilistic approaches have been proposed to mitigate the impact of this inherent phenomenon. However, most of these techniques are inadequate in reducing the number of redundant retransmissions while still guaranteeing that all nodes receive the packet. Further, in most cases they use a predetermined forwarding probability value for all nodes in the network which is quite unlikely to be optimal in other network set up. In this paper, we propose a new dynamic probabilistic counter-based broadcast scheme that can dynamically compute the forwarding probability at a node based on its neighbourhood information. Simulation results show that the new broadcast scheme achieves superior performance in terms of retransmitting nodes, collision rate, and end-to-end delay without sacrificing reachability compared to the existing schemes.

Modelling fully-adaptive routing in hypercubes

Analytical models for wormhole‐routed hypercubes with deterministic routing have been widely reported in the literature. A model for the hypercube with fully‐adaptive routing has recently been proposed in [1]. It uses M/M/1 queues, and computes a different probability of blocking at each intermediate router along the message path. As a result, the number of equations, and thus the computation steps, to evaluate latency increases with the network size. This paper proposes an alternative model that uses M/G/1 queues, and requires a constant number of computation steps irrespective of the network size. It achieves this by computing only once the mean probability of blocking across the entire path, and using it to determine the blocking time at a given router. Simulation experiments reveal that the model yields accurate latency results.

Comparative evaluation of contiguous allocation strategies on 3D mesh multicomputers

The performance of contiguous allocation strategies can be significantly affected by the type of the distribution adopted for job execution times. In this paper, the performance of the existing contiguous allocation strategies for 3D mesh multicomputers is re-visited in the context of heavy-tailed distributions (e.g., a Bounded Pareto distribution). The strategies are evaluated and compared using simulation experiments for both First-Come-First-Served (FCFS) and Shortest-Service-Demand (SSD) scheduling strategies under a variety of system loads and system sizes. The results show that the performance of the allocation strategies degrades considerably when job execution times follow a heavy-tailed distribution. Moreover, SSD copes much better than FCFS scheduling strategy in the presence of heavy-tailed job execution times. The results also reveal that allocation strategies that employ a list of allocated sub-meshes for both allocation and de-allocation exhibit low allocation overhead, and maintain good system performance in terms of average turnaround time and mean system utilization.