Papers by Lewis Mackenzie
2021 3rd IEEE Middle East and North Africa COMMunications Conference (MENACOMM), 2021
The use of Graph Routing in Wireless Highway Addressable Remote Transducer (WirelessHART) network... more The use of Graph Routing in Wireless Highway Addressable Remote Transducer (WirelessHART) networks offers the benefit of increased reliability of communications because of path redundancy and multi-hop network paths. Nonetheless, Graph Routing in a WirelessHART network creates a hotspot challenge resulting from unbalanced energy consumption. This paper proposes the use of unequal clustering algorithms based on Graph Routing in WirelessHART networks to help with balancing energy consumption, maximizing reliability, and reducing the number of hops in the network. Graph Routing is compared with pre-set and probabilistic unequal clustering algorithms in terms of energy consumption, packet delivery ratio, throughput and average end-to-end delay. A simulation test reveals that Graph Routing has improved energy consumption, throughput and reduced average end-to-end delay when conducted using probabilistic unequal clustering algorithms. However, there is no significant change in the packet delivery ratio, as most packets reach their destination successfully anyway.
Proceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000
Several analytical models of fully-adaptive routing have recently been proposed for wormhole-rout... more Several analytical models of fully-adaptive routing have recently been proposed for wormhole-routed k-ary ncubes under the uniform traffic pattern. However, there has been hardly any model reported yet that deals with other important non-uniform traffic patterns, such as hot spots. As a result, most studies have resorted to simulation when evaluating the performance merits of adaptive routing. This paper describes the first analytical model of fully-adaptive wormhole routing in k-ary n-cubes in the presence of hot spot traffic. Results from simulation show close agreement with those predicted by the model.
2008 IEEE International Symposium on Parallel and Distributed Processing, 2008
Proceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000, 2000
It exploits several communication techniques on stars in a novel way which can be adapted for com... more It exploits several communication techniques on stars in a novel way which can be adapted for computing similar functions. The algorithm is optimal and consists of three phases: initialization, main and final. While there is no computation in the initialization phase, the main phase is composed of n!/2 steps, each consisting of four multiplications, four subtractions and one communication operation, and an additional step including one division and one multiplication. The final phase is carried out in (n-1) sub-phases each with O(log n) steps where each step takes three communications and one addition.
Proceedings of the 2002 ACM symposium on Applied computing - SAC '02, 2002
A new analytical model for predicting message delay in wormhole-routed torus is presented. Unlike... more A new analytical model for predicting message delay in wormhole-routed torus is presented. Unlike previous wormhole routing models, which mainly have been developed for uniform traffic, the model introduced in this paper computes message latency in the wormhole-routed toms in the presence of broadcast traffic. Results, obtained through simulation experiments show that the model exhibits a good degree of accuracy in predicting message latency under different working conditions.
2007 IEEE/ACS International Conference on Computer Systems and Applications, 2007
Two strategies are used for the allocation of jobs to processors connected by mesh topologies: co... more Two strategies are used for the allocation of jobs to processors connected by mesh topologies: contiguous allocation and non-contiguous allocation. In noncontiguous allocation, a job request can be split into smaller parts that are allocated to non-adjacent free submeshes rather than always waiting until a single submesh of the requested size and shape is available. Lifting the contiguity condition is expected to reduce processor fragmentation and increase system utilization. However, the distances traversed by messages can be long, and as a result the communication overhead, especially contention, is increased. The extra communication overhead depends on how the allocation request is partitioned and assigned to free sub-meshes. This paper presents a new Non-contiguous allocation algorithm, referred to as Greedy-Available-Busy-List (GABL for short), which can decrease the communication overhead among processors allocated to a given job. The simulation results show that the new strategy can reduce the communication overhead and substantially improve performance in terms of parameters such as job turnaround time and system utilization. Moreover, the results reveal that the Shortest-Service-Demand-First (SSD) scheduling strategy is much better than the First-Come-First-Served (FCFS) scheduling strategy.
2007 International Conference on Parallel and Distributed Systems, 2007
The performance study of the existing noncontiguous processor allocation strategies has been trad... more The performance study of the existing noncontiguous processor allocation strategies has been traditionally carried out by means of simulation based on a stochastic workload model to generate a stream of incoming jobs that are submitted to and run on a given message passing parallel machine for a period of time. To validate the performance of the existing allocation algorithms, there has been need to evaluate the algorithms' performance based on a real workload trace. In this study, we evaluate the performance of several well-known processor allocation and job scheduling strategies based on a real workload trace and compare the results against those obtained from using a stochastic workload. Our results reveal that the conclusions reached on the relative performance merits of the allocation strategies when a real workload trace is used are in general compatible with those obtained when a stochastic workload is used.
Proceedings of the 11th IEEE/IFIP Annual Conference on Wireless On-demand Network Systems and Services, 2014
An Accident Warning System (AWS) is a safety application that provides collision avoidance notifi... more An Accident Warning System (AWS) is a safety application that provides collision avoidance notifications for next generation vehicles whilst Vehicular Ad-hoc Networks (VANETs) provide the communication functionality to exchange these notifications. Despite much previous research, there is little agreement on the requirements for accident warning systems. In order to build a practical warning system, it is important to ascertain the system requirements, information to be exchanged, and protocols needed for communication between vehicles. This paper presents a practical model of an accident warning system by stipulating the requirements in a realistic manner and thoroughly reviewing previous proposals with a view to identify gaps in this area.
On the performance merits of bypass channels in hypermeshes and k-ary n-cubes
The Computer Journal, 1999
Broadcasting in mobile ad hoc networks has traditionally been based on flooding, which swamps the... more Broadcasting in mobile ad hoc networks has traditionally been based on flooding, which swamps the network with large number of rebroadcast packets in order to reach all network nodes. The appropriate use of probabilistic broadcasting can reduce the number of packet transmission, effectively alleviating the problem of contention. In particular, a good probabilistic broadcast protocol can achieve higher saved rebroadcast and higher reachability. This paper presents a new probabilistic approach that dynamically adjusts the rebroadcasting probability as per the node distribution and node movement. This is done based on locally available information and without requiring any assistance of distance measurements or exact location determination devices. We evaluate the performance of our approach by comparing it with simple flooding as well as a fixed probabilistic approach. The results show that the new algorithm exhibits superior performance in terms of both the reachability and saved rebroadcasts.
Flooding is the simplest mechanism for broadcasting in mobile ad hoc networks (MANETs), where eac... more Flooding is the simplest mechanism for broadcasting in mobile ad hoc networks (MANETs), where each node retransmits a given broadcast packet exactly once. Despite its simplicity, flooding can result in high redundant retransmission, contention and collision, a phenomenon collectively referred to as the broadcast storm problem. Several probabilistic broadcast schemes have been proposed to mitigate this inherent phenomenon. However, probabilistic schemes that utilize a random assessment delay (RAD) mechanism suffer from poor performance in terms of end-to-end delay and reachability in congested networks. In this paper, we propose a new adaptive probabilistic counter-based broadcast scheme that enables a mobile node to adapt its RAD to reflect its current local congestion level. Simulation results reveal that this simple adaptation achieves superior performance in terms of saved rebroadcast, end-to-end delay and reachability over existing similar schemes.
Virtual channels have been introduced to enhance the performance of wormhole-switched networks. T... more Virtual channels have been introduced to enhance the performance of wormhole-switched networks. They are formed by arranging the buffer space dedicated to a given physical channel into multiple parallel buffers that share the physical bandwidth in a demand driven time-multiplexed manner. There have been few attempts to study the optimal arrangement of virtual channels (i.e. given a fixed amount of finite buffer what is the optimal way to arrange it into virtual channels). However, these studies have so fare resorted to simulation experiments and focused on deterministic routing algorithms. In this paper we use analytical performance models to investigate the optimal arrangement of the available buffer space into multiple virtual channels when adaptive routing is used in wormhole-switched k-ary n-cubes.
Broadcasting is a fundamental and frequently used operation in mobile ad hoc networks (MANETs). F... more Broadcasting is a fundamental and frequently used operation in mobile ad hoc networks (MANETs). Flooding, the process in which each node retransmits every uniquely received packet exactly once is the simplest and most commonly used mechanism for broadcasting in MANETs. Despite its simplicity, it can result in high redundancy, contention and collision, collectively known as broadcast storm problem. Counter-based broadcasting scheme has been proposed to overcome the broadcast storm problem in MANET. It relies on a threshold value to decide whether or not to forward a broadcast packet. The selection of an optimal counter threshold-value of this scheme is critical to improving saved rebroadcast without degrading reachability. Previous research work has focused on determining the best counter threshold-value based on low traffic injection conditions. In this paper, we investigate the best counter threshold value for optimal performance over a wide range of standard metrics in various network traffic injection rates. Simulation results reveal new insights in the performance of the counter-based broadcasting scheme and demonstrate its sensitivity to the selected threshold-values. These results are useful for optimally setting the counter threshold-value when designing efficient counter-based broadcasting schemes.
The collision probability in the MAC layer could become very high when a poor backoff algorithm i... more The collision probability in the MAC layer could become very high when a poor backoff algorithm is used, especially in dense networks. The Binary Exponential Backoff (BEB) used in the IEEE 802.11 MAC protocol uses a uniform random distribution to choose the backoff value. This often leads to reducing the effect of window size increment. This paper proposes a new backoff algorithm called "Fibonacci Increment Backoff (FIB)" in which the differences between consecutive contention window sizes are reduced. Results from simulation experiments reveal that the proposed algorithm achieves higher throughput than the BEB when used in a mobile ad hoc environment.
Multicast is the most primitive collective capability of any message-passing network. It is itsel... more Multicast is the most primitive collective capability of any message-passing network. It is itself central to many important parallel applications in Science and Engineering but are also fundamental to the implementation of higher-level communication operations such as gossip, gather, and barrier synchronisation. This paper presents a new efficient multicast path-based algorithm, which can achieve a high degree of parallelism and low communication latency over a wide range of traffic loads in the mesh. To achieve this, the proposed algorithm relies on a new approach that divides the destinations in a way that balances the traffic load on network channels during the propagation of the multicast message. Results from extensive simulations under a variety of working conditions confirm that the proposed algorithm exhibits superior performance characteristics over those of some well-known existing algorithms, such as dual-path, multiple-path, and column-path algorithms.
Blocking-ERS is an energy efficient route discovery algorithm for MANETs. It uses chase packets t... more Blocking-ERS is an energy efficient route discovery algorithm for MANETs. It uses chase packets to improve the route request process. In Blocking-ERS, most of the time the fulfilled route request manages to escape from the chase packet with the help of mobility. So its success rate in the catching process is low due to the immature discard of chase packets. In this report, we are proposing an improved algorithm named Blocking-ERS-Plus to overcome this deficiency in Blocking-ERS by allowing chase packets be broadcasted until the catching is insured to maximise the success rate. We provide detailed performance evaluation using simulation modelling and compare Blocking-ERS-Plus with both Blocking-ERS and AODV. Our findings show that Blocking-ERS-Plus outperforms both Blocking-ERS and AODV by reducing end-to-end delay due to the reduction in network congestion and by improving route request latency, routing overhead, and packet loss due to the higher success rate in the catching process which has positive impact on the network performance.
We introduce a new route discovery algorithm for MANETs using chase packets. The algorithm works ... more We introduce a new route discovery algorithm for MANETs using chase packets. The algorithm works by including the most likely destinations for a given source node in a local neighbourhood and broadcasting route requests at full speed within this region. Outside the neighbourhood however, propagation of the route requests is deliberately delayed to provide chase packets with an opportunity to catch up and minimise network congestion. The algorithm is adaptive and continuously updates the boundary of each source node's neighbourhood to optimise performance. Here, we provide a detailed performance evaluation and compare our algorithm with existing alternatives, to demonstrate that it does indeed improve the average chase time and the total broadcast bandwidth required.
Flooding is the simplest and commonly used mechanism for broadcasting in mobile ad hoc networks (... more Flooding is the simplest and commonly used mechanism for broadcasting in mobile ad hoc networks (MANETs). Despite its simplicity, it can result in high redundant retransmission, contention and collision in the network, a phenomenon referred to as broadcast storm problem. Several probabilistic broadcast schemes have been proposed to mitigate this problem inherent with flooding. Recently, we have proposed a hybrid-based scheme as one of the probabilistic scheme, which combines the advantages of pure probabilistic and counter-based schemes to yield a significant performance improvement. Despite these considerable numbers of proposed broadcast schemes, majority of these schemes' performance evaluation was based on random waypoint model. In this paper, we evaluate the performance of our broadcast scheme using a community based mobility model which is based on social network theory and compare it against widely used random waypoint mobility model. Simulation results have shown that using unrealistic movement pattern does not truly reflect on the actual performance of the scheme in terms of saved-rebroadcast, reachability and end to end delay.
Two strategies are used for the allocation of jobs to processors connected by mesh topologies: co... more Two strategies are used for the allocation of jobs to processors connected by mesh topologies: contiguous allocation and non-contiguous allocation. In non-contiguous allocation, a job request can be split into smaller parts that are allocated possibly non-adjacent free sub-meshes rather than always waiting until a single submesh of the requested size and shape is available. Lifting the contiguity condition is expected to reduce processor fragmentation and increase system utilization. However, the distances traversed by messages can be long, and as a result the communication overhead, especially contention, is increased. The extra communication overhead depends on how the allocation request is partitioned and assigned to free submeshes. This paper presents a new Non-contiguous allocation algorithm, referred to as Greedy-Available-Busy-List (GABL for short), which can decrease the communication overhead among processors allocated to a given parallel job. The GABL algorithm relies on a new approach that decomposes the allocation requests based on the sub-meshes available for allocation. This decreases the number of sub-meshes allocated to a job, hence decreases the distance traversed by messages, and which in turn decreases the communication overhead. In addition to allocation strategies, two job scheduling strategies, referred to as First-Come-First-Served (FCFS) and Shortest-Service-Demand-First (SSD) are studied, and they are used to compare the performance of allocation strategies. To evaluate the performance improvement achieved by our strategy and compare it against well-known existing non-contiguous and contiguous strategies, we conduct extensive simulation runs under the assumption of wormhole routing and two communication patterns, notably one-to-all and all-to-all. The results show that the new strategy can reduce the communication overhead and substantially improve performance in terms of parameters such as job turnaround time and system utilization. Moreover, the results reveal that the SSD scheduling strategy is much better than the FCFS scheduling strategy, therefore, the scheduling and allocation strategies both have substantial effect on the performance of contiguous and noncontiguous allocation strategies in 2D mesh.
Lecture Notes in Computer Science, 2001
This paper presents an analytical model for predicting latency of broadcast messages in adaptive ... more This paper presents an analytical model for predicting latency of broadcast messages in adaptive wormhole-routed Tori. Results obtained through simulation experiments show that the model exhibits a good degree of accuracy in predicting message latency.
Uploads
Papers by Lewis Mackenzie