{"title":"Importance sampling simulation of population overflow in two-node tandem networks","authors":"V. Nicola, T. S. Zaburnenko","doi":"10.1109/QEST.2005.15","DOIUrl":"https://doi.org/10.1109/QEST.2005.15","url":null,"abstract":"In this paper we consider the application of importance sampling in simulations of Markovian tandem networks in order to estimate the probability of rare events, such as network population overflow. We propose a heuristic methodology to obtain a good approximation to the 'optimal' state-dependent change of measure (importance sampling distribution). Extensive experimental results on 2-node tandem networks are very encouraging, yielding asymptotically efficient estimates (with bounded relative error) where no other state-independent importance sampling techniques are known to be efficient The methodology avoids the costly optimization involved in other recently proposed approaches to approximate the 'optimal' state-dependent change of measure. Moreover, the insight drawn from the heuristic promises its applicability to larger networks and more general topologies.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117272859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Introducing probability within state class analysis of dense-time-dependent systems","authors":"G. Bucci, R. Piovosi, L. Sassoli, E. Vicario","doi":"10.1109/QEST.2005.17","DOIUrl":"https://doi.org/10.1109/QEST.2005.17","url":null,"abstract":"Several techniques have been proposed for symbolic enumeration and analysis of the state space of reactive systems with nondeterministic temporal parameters taking values within a dense domain. In a large part of these techniques, the state space is covered by collecting states within equivalence classes each comprised of a discrete logical location and a dense variety of clock valuations encoded as a difference bounds matrix (DBM). The reachability relation among such classes enables qualitative verification of properties pertaining the ordering of events along critical runs and the satisfaction of stimulus/response deadlines. However, up to now, no results have been proposed which extend state class enumeration so as to combine the verification of the possibility of critical behaviors with a quantitative evaluation of their probability. In this paper, we extend the concept of equivalence classes based on DBM encoding with a density function which provides a measure for the probability associated with individual states collected in the class itself. To this end, we extend the formalism of time Petri nets by associating the static firing interval of each transition with a probability density function. We then expound how this probabilistic information determines a probability for the states collected within a class and how this probability evolves in the enumeration of the reachability relation among state classes. This opens the way to characterizing the possibility of critical behaviors with a quantitative measure of probability.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114579918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Challenges to evaluating Petaflops systems","authors":"T. Sterling","doi":"10.1109/QEST.2005.7","DOIUrl":"https://doi.org/10.1109/QEST.2005.7","url":null,"abstract":"Summary form only given. Even as the high performance computing community approaches 100 Teraflops Linpack performance, challenges to supercomputer hardware and software design may impede further progress and limit scalability and performance to cost. The assumed canonical methods of harnessing distributed resources are being severely stressed by the continued advances of Moore's law and system scaling as well as the complexities of emerging interdisciplinary applications. As we struggle into the Petaflops era, new models and metrics will be essential to guide all aspects of the evolution and application of future systems. A new generation of computer architecture such as the Cray Cascade system will employ its resources in potentially innovative ways quite different from today's prosaic commodity clusters (or MPPs). What those semantic and physical structures should look like and how they should be employed must be determined by aggressive application of a mix of modeling and evaluation techniques. While such methods in almost all cases have been explored, their use in the design and implementation of real world systems is currently limited. This presentation discusses the challenges to evaluating future generation Petaflops scale systems and the kinds of questions that needs to be answered that are usually not addressed in the early design cycle. Included for consideration are the baseline of optimality that should be used (today it is peak), measures of the impact of memory systems including concepts of temporal and spatial locality, cost functions for normalization of observed capabilities, and the role of statistical parametric tradeoff studies. In addition, this presentation briefly examines issues related to user productivity and the impact of system characteristics on them. This article concludes that among the most important trends in advanced high end computing is the dramatic potential of quantitative evaluation of systems.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122267509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A MAP fitting approach with independent approximation of the inter-arrival time distribution and the lag correlation","authors":"G. Horváth, M. Telek, P. Buchholz","doi":"10.1109/QEST.2005.1","DOIUrl":"https://doi.org/10.1109/QEST.2005.1","url":null,"abstract":"This paper proposes a two-step Markov arrival process (MAP) fitting approach, where the first step is the phase type fitting of the inter-arrival time and the second step is the approximation of the first n lag correlation values. Depending on the description of the arrival process to approximate various phase type fitting methods can be applied for the first step. In the second step the approximation of the lag correlation values is computed through a non-linear optimization problem. Numerical examples demonstrate the abilities and the limits of the fitting method.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127813037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Markov reward model checker","authors":"J. Katoen, M. Khattri, I. Zapreev","doi":"10.1109/QEST.2005.2","DOIUrl":"https://doi.org/10.1109/QEST.2005.2","url":null,"abstract":"This short tool paper introduces MRMC, a model checker for discrete-time and continuous-time Markov reward models. It supports reward extensions of PCTL and CSL, and allows for the automated verification of properties concerning long-run and instantaneous rewards as well as cumulative rewards. In particular it supports to check the reachability of a set of goal states (by only visiting legal states before) under a time and an accumulated reward constraint. Several numerical algorithms and extensions thereof are included in MRMC.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133738536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Steady state solution for models with geometric and finite support activity duration","authors":"A. Horváth","doi":"10.1109/QEST.2005.37","DOIUrl":"https://doi.org/10.1109/QEST.2005.37","url":null,"abstract":"This paper addresses steady state solution of discrete time stochastic models in which every activity duration is given either by a geometric or a finite support distribution. Finite support distributions can be described by discrete time phase type (DPH) distributions. The behaviour of the whole stochastic model is given by a discrete time Markov chain (DTMC). The DTMC is subject to the so-called state space explosion. We present a technique for obtaining the steady state solution that alleviates this problem. The technique is based on Gaussian elimination combined with an iterative technique.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115992631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Workload propagation - overload in bursty servers","authors":"Qi Zhang, Alma Riska, E. Riedel","doi":"10.1109/QEST.2005.43","DOIUrl":"https://doi.org/10.1109/QEST.2005.43","url":null,"abstract":"Internet servers are developing into complex but central components in the information infrastructure and are accessed by an ever-increasing and diversified user population. As such, they are susceptible to unpredicted and transient overloads, making highly available, yet cost-effective service a critical challenge. System responsiveness during overload periods is at least as important as system behavior under average, steady state load. Using measurements from a 3-tier e-commerce server, we show how normal and overload conditions propagate through the system hierarchy, i. e., from the front-end server to the back-end database, focusing on CPU, memory, and I/O performance. We find that overload conditions at lower system levels occur not only when the number of users in the system increases, but also during rapid changes in the nature of the work requested by the current users. These observations advocate the development of system mechanisms at the lower levels that can detect overload and self-adapt their configuration parameters in order to ensure high service availability and graceful performance degradation. We illustrate the effectiveness of a scheduling mechanism at the disk and provide a proof of concept that such self-adaptive scheduling mechanisms at the lower levels are a step toward faster system recovery under conditions of transient overload, and can thus complement admission control at the front end.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127142087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Draw-Net, a customizable multi-formalism, multi-solution tool for the quantitative evaluation of systems","authors":"M. Gribaudo, D. Raiteri, G. Franceschinis","doi":"10.1109/QEST.2005.10","DOIUrl":"https://doi.org/10.1109/QEST.2005.10","url":null,"abstract":"This paper presents the last version of Draw-Net, a customizable tool for the design and solution of models expressed in any graph based formalism, including the possibility of representing complex models by means of multi-formalism and analyzing them by exploiting different solution modules. In particular, it focuses on the new tools and features available in the current version of the framework.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125036998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SAM: a tool for software architecture modeling & performance analysis","authors":"G. Rajeshwari, S. Sarkar","doi":"10.1109/QEST.2005.32","DOIUrl":"https://doi.org/10.1109/QEST.2005.32","url":null,"abstract":"This paper presents SAM (software architecture modeling & analysis), a set of tools that capture the workload model, performance objectives, and helps the architect to identify an appropriate architecture of a software intensive system. To begin with, the architect captures the AS-IS architecture with performance constraints. This is assessed by building a layered queuing network (LQN) and solved using discrete event simulation (DES). The tool then allows the architects to apply a set of architectural tactics and reassess the architecture. This helps the architect to perform a series of successive refinements iteratively and eventually move towards an appropriate architecture that meets the performance objectives.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132839908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Gribaudo, Francesco Moscato, N. Mazzocca, V. Vittorini
{"title":"Multisolution of complex performability models in the OsMoSys/DrawNET framework","authors":"M. Gribaudo, Francesco Moscato, N. Mazzocca, V. Vittorini","doi":"10.1109/QEST.2005.22","DOIUrl":"https://doi.org/10.1109/QEST.2005.22","url":null,"abstract":"In the last years some infrastructures and frameworks have been proposed to enable the compositional development of multiformalism models. The OsMoSys/DrawNET framework allows to develop and analyze complex performability models which are composed by several submodels expressed by means of different formal languages. In this paper we describe the approach to multisolution of multiformalism models in the OsMoSys/DrawNET framework and we introduce the mechanisms used to define the performance indices and generate the required results.","PeriodicalId":256187,"journal":{"name":"Second International Conference on the Quantitative Evaluation of Systems (QEST'05)","volume":"439 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122886645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}