PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348192
N. Gülpinar, P. Harrison, B. Rustem, L. Pau
{"title":"An optimisation model for a two-node router network","authors":"N. Gülpinar, P. Harrison, B. Rustem, L. Pau","doi":"10.1109/MASCOT.2004.1348192","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348192","url":null,"abstract":"Architectural designs for routers and networks of routers to support mobile communication are analysed for their end-to-end performance using a simple Markov model. In view of the diverse design options, such models have many adjustable parameters and choosing the best set for a particular performance objective is a delicate and time-consuming task. We introduce an optimisation approach to automate this task, illustrated in a two-node, tandem network of routers with finite capacity and recovery buffers. We minimise the mean end-to-end delay subject to an upper limit on the rate of losses, which may be due to either full buffers or corrupted data. Losses at a full buffer are inferred by a time-out, whereas corrupted data is detected immediately on receipt of a packet at a router, causing a N-ACK to be sent upstream. Recovery buffers hold successfully transmitted packets so that, on receiving a N-ACK, the packet, if present, can be retransmitted, avoiding an expensive resend from source. Hence, a critical parameter that affects both loss rate and transmission time is the ratio of arrival-buffer size to recovery-buffer size. We develop a queueing model of this network and present graphs showing how end-to-end delay varies with certain parameter combinations. The tedious nature of trying to find the best parameter values in this way motivates our formal optimisation which yields optimal parameter values directly from the model specification using standard software.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"186 1","pages":"147-156"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80601059","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348235
P. Chandra, A. Kshemkalyani
{"title":"Causal multicast in mobile networks","authors":"P. Chandra, A. Kshemkalyani","doi":"10.1109/MASCOT.2004.1348235","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348235","url":null,"abstract":"Distributed applications using file sharing and file replication, conferencing, and delivery in multimedia systems often need to use the semantics of causal multicast. Causal multicast in a mobile system is complicated by the various limitations imposed by the mobile system. Though there are different directions to improve the performance of causal multicast algorithms in mobile systems, at the core of such algorithms is the module to impose causal delivery among a set of nodes, which may be either mobile hosts, or mobile service stations, or peers at a higher level in the interconnection hierarchy. We show how to adapt the optimal causal multicast algorithm of Kshemkalyani-Singhal to mobile networks, and then show simulation results comparing its performance with that of other algorithms for causal multicast in mobile networks.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"21 1","pages":"213-220"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74343322","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348280
D. Menascé, E. Casalicchio
{"title":"A framework for resource allocation in grid computing","authors":"D. Menascé, E. Casalicchio","doi":"10.1109/MASCOT.2004.1348280","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348280","url":null,"abstract":"Grid computing is the future computing paradigm for enterprise applications. An enterprise application running on a grid is composed of a set of SLA-constrained sub-tasks demanding different types of services and resources such as processors, data storage, service providers, and network links. The paper formalizes the resource allocation problem for SLA-constrained grid applications. The paper considers a very general case in which applications are decomposed into tasks that exhibit precedence relationships. The problem consists in finding the optimal resource allocation that minimizes total cost while preserving execution time service level agreements (SLAs). The paper provides a framework for building heuristic solutions for this NP-hard problem, presents an example of such a heuristic, and provides a numerical example.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"5 1","pages":"259-267"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88660065","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348283
X. Dimitropoulos, G. Riley
{"title":"Large-scale simulation models of BGP","authors":"X. Dimitropoulos, G. Riley","doi":"10.1109/MASCOT.2004.1348283","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348283","url":null,"abstract":"The complex nature of the border gateway protocol (BGP) is not amenable to analytical modeling, and thus simulation-based analysis methods are needed to understand its behavior. To this end, we investigate techniques that make large-scale BGP simulations feasible. The described techniques partially ameliorate the memory and execution time bottlenecks to yield large-scale BGP simulations. Our focus is cast on efficient sharing of BGP routing tables, execution time optimizations for simulation trials, and proper partitioning of parallel distributed BGP simulations. Moreover, we survey the requirements for realistic, Internet-like BGP simulations and develop a simulation toolset to expedite realistic configuration of a BGP simulator.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"20 1","pages":"287-294"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83775561","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348197
Nuno Pereira, E. Tovar, L. M. Pinho
{"title":"INDEPTH: timeliness assessment of Ethernet/IP-based systems","authors":"Nuno Pereira, E. Tovar, L. M. Pinho","doi":"10.1109/MASCOT.2004.1348197","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348197","url":null,"abstract":"The continuous improvement of Ethernet technologies is boosting the eagerness of extending their use to cover factory-floor distributed real time applications. Indeed, it is remarkable the considerable amount of research work that has been devoted to the timing analysis of Ethernet-based technologies in the past few years. It happens, however, that the majority of those works are restricted to the analysis of sub-sets of the overall computing and communication system, thus without addressing timeliness in a holistic fashion. To this end, we address an approach, based on simulation, aiming at extracting temporal properties of commercial-off-the-shelf (COTS) Ethernet-based factory-floor distributed systems. This framework is applied to a specific COTS technology, Ethernet/IP. We reason about the modeling and simulation of Ethernet/IP-based systems, and on the use of statistical analysis techniques to provide useful results on timeliness. The approach is part of a wider framework related to the research project INDEPTH NDustrial-Ethernet ProTocols under Holistic analysis.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"31 1","pages":"192-201"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88950905","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348290
Mingwei Gong, C. Williamson
{"title":"Simulation evaluation of hybrid SRPT scheduling policies","authors":"Mingwei Gong, C. Williamson","doi":"10.1109/MASCOT.2004.1348290","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348290","url":null,"abstract":"This paper uses trace-driven simulations to evaluate two novel Web server scheduling policies called K-SRPT and T-SRPT. K-SRPT is a multi-threaded version of SRPT (shortest remaining processing time) that can have up to K jobs in service at a time. T-SRPT is a hybrid policy that dynamically switches from PS (processor sharing) to SRPT when the number of jobs in the system exceeds T, and back to PS when the load diminishes. Slowdown profile plots are used to analyze the performance of these policies relative to PS, SRPT, and FSP (fair sojourn protocol). Simulation results show that these new parameterized policies offer smooth performance tradeoffs between SRPT and PS. Stability issues for T-SRPT are also discussed.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"22 1","pages":"355-363"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86010988","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348255
P. Harrison, Ting Ting Lee
{"title":"A new recursive algorithm for computing generating functions in closed multi-class queueing networks","authors":"P. Harrison, Ting Ting Lee","doi":"10.1109/MASCOT.2004.1348255","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348255","url":null,"abstract":"We obtain an algorithm that implements a recursive generating function (RGF) for computing the normalising constant in closed, multi-class, product-form queueing networks with multiple, load-independent servers of the same load. It expresses the generating function of a q-class network in terms of the generating functions of a set of (q-1)-class networks. The result for a multi-class network can therefore be deduced hierarchically by finding the normalising constants of a collection of single class networks. A storage management scheme is devised, based on a depth-first recursion tree traversal, to optimise both time and storage requirements and the numerical precision of the resulting RGF algorithm is investigated. In two-class networks, the space and time requirements of RGF are shown to be smaller than for the convolution and RECAL algorithms when the networks contain a moderate to large number of customers. With more classes, RGF gives better performance than the other two methods in many-node networks that are organised in a few groups of several identical nodes.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"48 1","pages":"231-238"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87874202","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348293
A. Mahdy, J. Deogun, Shashank K. Mehta
{"title":"End-to-end delay heuristics for adaptive optical wireless networks","authors":"A. Mahdy, J. Deogun, Shashank K. Mehta","doi":"10.1109/MASCOT.2004.1348293","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348293","url":null,"abstract":"Wireless communications offer an attractive option for many military, commercial as well as personal communication needs because of flexibility, cost effectiveness, and mobility. The quality features of wireless communications have led to tremendous growth in the development of novel technologies that raise the need for broadband wireless communications. Optical wireless systems offer high transmission rates that can accommodate these broadband needs. Optical wireless links can be prone to the atmosphere, which can result in a performance degradation. Therefore, optical wireless networks should be adaptive with flexible links. In this paper we emphasize the adaptability of optical wireless networks and propose new heuristics for the optimization of communication delay in a flexible link regime for networks with unbounded degree transceivers. Extensive simulations are conducted to evaluate the performance of the proposed heuristics and validate the improvement in network functionality as compared to the unadaptable environment. Empirical results show that a 50% reduction in average packet delay, as compared to unadaptable networks, can be achieved by a network based on the proposed heuristics.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"13 1","pages":"383-390"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78603650","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}
PerformancePub Date : 2004-10-04DOI: 10.1016/j.adhoc.2005.06.005
R. M. D. Moraes, H. Sadjadpour, J. Garcia-Luna-Aceves
{"title":"On mobility-capacity-delay trade-off in wireless ad hoc networks","authors":"R. M. D. Moraes, H. Sadjadpour, J. Garcia-Luna-Aceves","doi":"10.1016/j.adhoc.2005.06.005","DOIUrl":"https://doi.org/10.1016/j.adhoc.2005.06.005","url":null,"abstract":"","PeriodicalId":32394,"journal":{"name":"Performance","volume":"80 1","pages":"12-19"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79315152","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}
PerformancePub Date : 2004-10-04DOI: 10.1109/MASCOT.2004.1348189
M. Kwiatkowska, D. Parker, Yi Zhang, Rashid Mehmood
{"title":"Dual-processor parallelisation of symbolic probabilistic model checking","authors":"M. Kwiatkowska, D. Parker, Yi Zhang, Rashid Mehmood","doi":"10.1109/MASCOT.2004.1348189","DOIUrl":"https://doi.org/10.1109/MASCOT.2004.1348189","url":null,"abstract":"We describe the dual-processor parallelisation of a symbolic (BDD-based) implementation of probabilistic model checking. We use multi-terminal BDDs (binary decision diagrams), which allow a compact representation of large, structured Markov chains. We show that they also provide a convenient block decomposition of the Markov chain which we use to implement a parallelised version of the Gauss-Seidel iterative method. We provide experimental results on a range of case studies to illustrate the effectiveness of the technique, observing an average speed-up of 1.8 with two processors. Furthermore, we present an optimisation for our method based on preconditioning.","PeriodicalId":32394,"journal":{"name":"Performance","volume":"19 1","pages":"123-130"},"PeriodicalIF":0.0,"publicationDate":"2004-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85345324","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}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
