By Topic

Computers and Digital Techniques, IEE Proceedings -

Issue 2 • Date Mar 2003

Filter Results

Displaying Results 1 - 6 of 6
  • Approximate solution of PEPA models using component substitution

    Page(s): 67 - 74
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (854 KB)  

    Performance models specified using compositional algebra suffer the well-known state space explosion problem, where a relatively small definition leads to a Markov chain with a large state space that is problematic to solve. As a result it is widely recognised that the development of techniques to solve performance models efficiently is of particular practical importance. Recently the notion of behavioural independence was introduced to exploit the structure of Markovian process algebra models in order to solve models in a compositional manner. The opposite property, namely control, is now used to solve models by substituting components in the model with simpler versions. The approach is validated through two examples and by deriving a variety of performance measures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local grid scheduling techniques using performance prediction

    Page(s): 87 - 96
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1429 KB)  

    The use of computational grids to provide an integrated computer platform, composed of differentiated and distributed systems, presents fundamental resource and workload management questions. Key services such as resource discovery, monitoring and scheduling are inherently more complicated in a grid environment where the resource pool is large, dynamic and architecturally diverse. The authors approach the problem of grid workload management through the development of a multi-tiered scheduling architecture (TITAN) that employs a performance prediction system (PACE) and task distribution brokers to meet user-defined deadlines and improve resource usage efficiency. Attention is focused on the lowest tier which is responsible for local scheduling. By coupling application performance data with scheduling heuristics, the architecture is able to balance the processes of minimising run-to-completion time and processor idle time, whilst adhering to service deadlines on a per-task basis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance comparison of deadlock recovery and deadlock avoidance routing algorithms in wormhole-switched networks

    Page(s): 97 - 106
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (975 KB)  

    Dealing with deadlock has always been a crucial issue for any routing algorithms proposed for wormhole-switched networks. Adaptive routing algorithms, based on deadlock avoidance strategies, usually dedicate resources specifically to ensure deadlock freedom. However, a number of recent studies have demonstrated that deadlocks are quite rare in the network. This fact has motivated researchers to introduce adaptive routing algorithms based on deadlock recovery strategies. In an effort to gain a deep understanding of the factors that affect routing performance, a comparison of the performance merits of deadlock recovery against deadlock avoidance routing algorithms is performed. While most existing network evaluation studies have been based on software simulation, the present study is the first to use the analytical modelling approach to conduct the comparative analysis. The results reveal that in most cases deadlock recovery routing algorithms exhibit superior performance characteristics over their deadlock avoidance counterparts. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance partitioning impact in distributed simulation of high-level algebraic Petri nets

    Page(s): 121 - 132
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1447 KB)  

    A class of Petri nets called high-level algebraic nets is studied. Attention is focused on ECATNets (extended concurrent algebraic term nets), a kind of high-level algebraic Petri net with bounded capacity places. Three distributed simulators are presented that are able to simulate ECATNet models: asynchronous conservative, asynchronous optimistic and synchronous. The influence that factors such as the characteristics of the simulated models, their initial partitioning, the organisation of the simulators and the characteristics of the target multicomputer have in the performance of the simulations have been measured and characterised. Experiments are reported that have been executed with those simulators, with the aim of characterising how the partitioning of the ECATNet model, the synchronisation strategy and the ways of organising the simulator influence the achieved performance. It is concluded that distributed simulation of ECATNets on a multicomputer system can in fact gain speedup over the sequential simulation, and this can be achieved even for small scale simulation models. An analysis of the results allows the suggestion of suitable combinations of algorithms to efficiently carry out simulations of ECATNet models. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance modelling with the Unified Modelling Language and stochastic process algebras

    Page(s): 107 - 120
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (3386 KB)  

    A software toolset which allows Unified Modelling Language (UML) modellers to annotate models with performance information is described. An equivalent performance model is extracted from the UML, solved, and the results reflected back to the UML level. Used in this way, the toolset gives a high-level approach to software performance modelling where the benefits of the performance modelling process are achieved without significant additional notational burden. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance modelling of GPRS with bursty multiclass traffic

    Page(s): 75 - 85
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1162 KB)  

    An analytic framework is devised, based on the principle of maximum entropy (ME), for the performance modelling and evaluation of a wireless GSM/GPRS cell supporting bursty multiple class traffic of voice calls and data packets under complete partitioning (CPS), partial sharing (PSS) and aggregate sharing (ASS) traffic handling schemes. Three distinct open queueing network models (QNMS) under CPS, PSS and ASS, respectively, are described, subject to external compound Poisson traffic processes and generalised exponential (GE) transmission times under a repetitive service blocking mechanism and a complete buffer sharing management rule. Each QNM generally consists of three building block stations, namely a loss system with GSM/GPRS traffic and a system of access and transfer finite capacity queues in tandem dealing with GPRS traffic under head-of-line and discriminatory processor sharing scheduling disciplines, respectively. The analytic methodology is illustrated by focusing on the performance study of the GE-type tandem queueing system for GPRS under a CPS. An ME product-form approximation is characterised leading into a decomposition of the tandem system into individual queues and closed-form ME expressions for state and blocking probabilities are presented. Typical numerical examples are included to validate the ME solutions against simulation and study the effect of external GPRS bursty traffic upon the performance of the cell. Moreover, an overview of recent extensions of the work towards the analysis of a GE-type multiple server finite capacity queue with preemptive resume priorities and its implications towards the performance modelling and evaluation of GSM/GPRS cells with PSS and ASS are included. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.