Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284456
C. Carothers, R. Fujimoto, Yi-Bing Lin, P. England
There has been rapid growth an demand for mobile communications over the past few years that has led to intensive research and development of complex PCS (personal communication service) networks. Capacity planning and performance modeling are necessary to maintain a high quality of service to the mobile subscriber while minimizing the cost. Simulation is widely used in such studies, however, because these models are extremely time consuming to execute, only small-scale PCS networks have previously been simulated. In this paper, we examine the use of the Time Warp distributed simulation mechanism in simulating large scale (1024 or more cells) PCS networks. An object-oriented, distributed, discrete event simulator using Time Warp has been developed, and initial performance measurements completed. Speedups in the range of 2.8 to 7.8 using 8 Unix workstations have been obtained, enabling simulation runs that require 20 hours on a single workstation to be completed in only 3.5 hours.<>
{"title":"Distributed simulation of large-scale PCS networks","authors":"C. Carothers, R. Fujimoto, Yi-Bing Lin, P. England","doi":"10.1109/MASCOT.1994.284456","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284456","url":null,"abstract":"There has been rapid growth an demand for mobile communications over the past few years that has led to intensive research and development of complex PCS (personal communication service) networks. Capacity planning and performance modeling are necessary to maintain a high quality of service to the mobile subscriber while minimizing the cost. Simulation is widely used in such studies, however, because these models are extremely time consuming to execute, only small-scale PCS networks have previously been simulated. In this paper, we examine the use of the Time Warp distributed simulation mechanism in simulating large scale (1024 or more cells) PCS networks. An object-oriented, distributed, discrete event simulator using Time Warp has been developed, and initial performance measurements completed. Speedups in the range of 2.8 to 7.8 using 8 Unix workstations have been obtained, enabling simulation runs that require 20 hours on a single workstation to be completed in only 3.5 hours.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114982379","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284399
H. Herpel, M. Held, M. Glesner
This paper presents a design and simulation environment to support the validation of design concepts for embedded systems during early design phases. The tool is built around a methodology based on rapid prototyping. The MCEMS Toolbox supports the designer during the architectural, detailed design and implementation phase with a set of models, software and hardware for system description, prototype synthesis and execution under real-time conditions. Thus, specifications can be validated during early design phases which shortens the overall development time.<>
{"title":"MCEMS Toolbox/spl minus/a hardware-in-the-loop simulation environment for mechatronic systems","authors":"H. Herpel, M. Held, M. Glesner","doi":"10.1109/MASCOT.1994.284399","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284399","url":null,"abstract":"This paper presents a design and simulation environment to support the validation of design concepts for embedded systems during early design phases. The tool is built around a methodology based on rapid prototyping. The MCEMS Toolbox supports the designer during the architectural, detailed design and implementation phase with a set of models, software and hardware for system description, prototype synthesis and execution under real-time conditions. Thus, specifications can be validated during early design phases which shortens the overall development time.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115943660","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284416
T. Routen
This paper examines the utility of genetic algorithms and neural nets for optimization problems occurring in local access network design. It contrasts an existing Hopfield net approach to concentrator assignment with a genetic algorithm approach and finds that the genetic algorithm performs better, while offering greater generality. It describes how genetic algorithms may also be used to solve terminal layout problems, and introduces a representation and special-purpose operators for the solution of concentrator layout problems.<>
{"title":"Genetic algorithm and neural network approaches to local access network design","authors":"T. Routen","doi":"10.1109/MASCOT.1994.284416","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284416","url":null,"abstract":"This paper examines the utility of genetic algorithms and neural nets for optimization problems occurring in local access network design. It contrasts an existing Hopfield net approach to concentrator assignment with a genetic algorithm approach and finds that the genetic algorithm performs better, while offering greater generality. It describes how genetic algorithms may also be used to solve terminal layout problems, and introduces a representation and special-purpose operators for the solution of concentrator layout problems.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116178866","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284437
H. Sharif, H. Vakilzadian, Hong Jiang
This paper presents a study of an interconnecting architecture between an array of processing elements and shared memory modules in a massively parallel computer system. This architecture is called Serial Link Interconnection Network (SLIN). SLIN is based on ultrahigh-throughput (more than one gigabits per second) bi-directional serial links. These links connect serially ported processing elements and memory modules through a network of switches. The interconnection network places the outer columns of the switches in a tree topology while the innermost columns are linked point to point. The results of the SLIN computer models' simulations are analyzed. The findings show the advantages of SLIN architecture in terms of cost-effectiveness and link utilization.<>
{"title":"Design and simulations of a serial-link interconnection network for a massively parallel computer system","authors":"H. Sharif, H. Vakilzadian, Hong Jiang","doi":"10.1109/MASCOT.1994.284437","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284437","url":null,"abstract":"This paper presents a study of an interconnecting architecture between an array of processing elements and shared memory modules in a massively parallel computer system. This architecture is called Serial Link Interconnection Network (SLIN). SLIN is based on ultrahigh-throughput (more than one gigabits per second) bi-directional serial links. These links connect serially ported processing elements and memory modules through a network of switches. The interconnection network places the outer columns of the switches in a tree topology while the innermost columns are linked point to point. The results of the SLIN computer models' simulations are analyzed. The findings show the advantages of SLIN architecture in terms of cost-effectiveness and link utilization.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122890117","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284392
B. Malloy
We compare the program-driven and trace-driven approach to simulating the parallel execution of a program on a multiprocessor. To obtain the traces, we used a program-driven simulator that actually executes the instructions in an input program. Our simulator is coded in the process-oriented simulation language SimCal and is guided by a parameterized computational model that describes the target multiprocessor. We have used the program-driven multiprocessor simulator to execute parallel threads produced by our parallelizing compiler and we have validated the simulator by comparing the simulation results to results obtained through execution of the threads on an actual multiprocesser, the AT&T 3B2. To compare the trace-driven and program-driven approaches, we used the program-driven simulator to obtain traces of the execution of the threads. We conclude that the trace-driven approach is faster than the program-driven approach since it doesn't actually execute the threads. However, the trace-driven approach must store the traces and therefore requires more space than the program-driven approach.<>
{"title":"Trace-driven and program-driven simulation: a comparison","authors":"B. Malloy","doi":"10.1109/MASCOT.1994.284392","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284392","url":null,"abstract":"We compare the program-driven and trace-driven approach to simulating the parallel execution of a program on a multiprocessor. To obtain the traces, we used a program-driven simulator that actually executes the instructions in an input program. Our simulator is coded in the process-oriented simulation language SimCal and is guided by a parameterized computational model that describes the target multiprocessor. We have used the program-driven multiprocessor simulator to execute parallel threads produced by our parallelizing compiler and we have validated the simulator by comparing the simulation results to results obtained through execution of the threads on an actual multiprocesser, the AT&T 3B2. To compare the trace-driven and program-driven approaches, we used the program-driven simulator to obtain traces of the execution of the threads. We conclude that the trace-driven approach is faster than the program-driven approach since it doesn't actually execute the threads. However, the trace-driven approach must store the traces and therefore requires more space than the program-driven approach.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122890769","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284455
Kishor S. Trivedi, M. Malhotra, R. M. Fricks
Performability and reliability modeling techniques and tools have been an area of intensive research activity in the last ten years. We present a unified mathematical framework for performability and reliability models in terms of Markov reward models. The framework presented is not the only one available for performability analysis, but it is the most commonly used one. To complete our exposition, we describe two modeling software packages: SHARPE (Symbolic Hierarchical Automated Reliability/Performance Evaluator) and SPNP (Stochastic Petri Net Package).<>
{"title":"Markov reward approach to performability and reliability analysis","authors":"Kishor S. Trivedi, M. Malhotra, R. M. Fricks","doi":"10.1109/MASCOT.1994.284455","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284455","url":null,"abstract":"Performability and reliability modeling techniques and tools have been an area of intensive research activity in the last ten years. We present a unified mathematical framework for performability and reliability models in terms of Markov reward models. The framework presented is not the only one available for performability analysis, but it is the most commonly used one. To complete our exposition, we describe two modeling software packages: SHARPE (Symbolic Hierarchical Automated Reliability/Performance Evaluator) and SPNP (Stochastic Petri Net Package).<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123736121","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284380
F. L. Presti, M. Colajanni, Salvatore Tucci
We obtain stochastic bounds on execution times of parallel computations assuming ideal conditions for shared resources. A parallel computation is modelled as a task system with precedence constraints expressed as a directed acyclic graph (DAG). The task execution times are assumed independent random variables. The performance measure considered is the overall execution time of the computation. To obtain upper bounds on this measure, we apply stochastic ordering and stochastic comparison techniques.<>
{"title":"Stochastic bounds on execution times of parallel computations","authors":"F. L. Presti, M. Colajanni, Salvatore Tucci","doi":"10.1109/MASCOT.1994.284380","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284380","url":null,"abstract":"We obtain stochastic bounds on execution times of parallel computations assuming ideal conditions for shared resources. A parallel computation is modelled as a task system with precedence constraints expressed as a directed acyclic graph (DAG). The task execution times are assumed independent random variables. The performance measure considered is the overall execution time of the computation. To obtain upper bounds on this measure, we apply stochastic ordering and stochastic comparison techniques.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125794528","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284408
M. Marsan, Andrea Bianco, L. Ciminiera, Riccardo Sisto, A. Valenzano
Performance analysis and formal correctness verification of computer communication protocols and distributed systems have traditionally been considered as two separate fields. However, their integration can be achieved by using formal description techniques as paradigms for performance modeling. The authors investigate the possibility of using LOTOS, one of the two formal specification languages that have been standardized by ISO, as the formal basis for performance modeling. A LOTOS extension which encompasses both timing and probabilistic aspects is proposed, and a general performance model derivable from extended LOTOS specification is identified. The performance model is open to different evaluation techniques. A simple example, a stop-and-wait protocol, is used to concretely demonstrate the new approach.<>
{"title":"Integrating performance analysis in the context of LOTOS-based design","authors":"M. Marsan, Andrea Bianco, L. Ciminiera, Riccardo Sisto, A. Valenzano","doi":"10.1109/MASCOT.1994.284408","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284408","url":null,"abstract":"Performance analysis and formal correctness verification of computer communication protocols and distributed systems have traditionally been considered as two separate fields. However, their integration can be achieved by using formal description techniques as paradigms for performance modeling. The authors investigate the possibility of using LOTOS, one of the two formal specification languages that have been standardized by ISO, as the formal basis for performance modeling. A LOTOS extension which encompasses both timing and probabilistic aspects is proposed, and a general performance model derivable from extended LOTOS specification is identified. The performance model is open to different evaluation techniques. A simple example, a stop-and-wait protocol, is used to concretely demonstrate the new approach.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121866647","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284383
D. Frosch-Wilke, Kasyap Natarajan
Demanding a certain structural property, derived by applying the principle of maximum entropy to single server systems, from the equilibrium-queue-length distribution of the M/G/1 system leads to the generalized exponential (GE) service time distribution. The G/GE/1 queue is analysed by means of spectrum factorization of Lindley's integral equation. We obtain explicit expressions for a job's waiting time and sojourn time distribution, and for the equilibrium-queue-length distribution seen by an arriving job as well as seen at an arbitrary instant of time; the last one satisfies the structural property for arbitrary arrival processes. Moreover, the G/GE/1 queue can play a central role in the maximum entropy analysis of general open queueing networks with FCFS single server stations.<>
{"title":"A maximum entropy analysis of the single server queue","authors":"D. Frosch-Wilke, Kasyap Natarajan","doi":"10.1109/MASCOT.1994.284383","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284383","url":null,"abstract":"Demanding a certain structural property, derived by applying the principle of maximum entropy to single server systems, from the equilibrium-queue-length distribution of the M/G/1 system leads to the generalized exponential (GE) service time distribution. The G/GE/1 queue is analysed by means of spectrum factorization of Lindley's integral equation. We obtain explicit expressions for a job's waiting time and sojourn time distribution, and for the equilibrium-queue-length distribution seen by an arriving job as well as seen at an arbitrary instant of time; the last one satisfies the structural property for arbitrary arrival processes. Moreover, the G/GE/1 queue can play a central role in the maximum entropy analysis of general open queueing networks with FCFS single server stations.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114658675","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}
Pub Date : 1994-01-31DOI: 10.1109/MASCOT.1994.284378
T. Uhl, J. Ulmer
Three tools for the graphical simulation of media access protocols are presented. The media access protocols concerned are CSMA/CD (Ethernet, IEEE 802.3), FDDI (IEEE 802.5) and DQDB (IEEE 802.6). The object of the tools is to explain the principle of the protocols by using graphics and motion-pictures on a computer display. Several states of the systems can be modelled, for example collisions (CSMA/CD) or link faults (FDDI). In the case of CSMA/CD and DQDB, it is also possible for the programs to carry out a simulation with the evaluation of performance aspects.<>
{"title":"Animated simulations of media access protocols in local area networks","authors":"T. Uhl, J. Ulmer","doi":"10.1109/MASCOT.1994.284378","DOIUrl":"https://doi.org/10.1109/MASCOT.1994.284378","url":null,"abstract":"Three tools for the graphical simulation of media access protocols are presented. The media access protocols concerned are CSMA/CD (Ethernet, IEEE 802.3), FDDI (IEEE 802.5) and DQDB (IEEE 802.6). The object of the tools is to explain the principle of the protocols by using graphics and motion-pictures on a computer display. Several states of the systems can be modelled, for example collisions (CSMA/CD) or link faults (FDDI). In the case of CSMA/CD and DQDB, it is also possible for the programs to carry out a simulation with the evaluation of performance aspects.<<ETX>>","PeriodicalId":288344,"journal":{"name":"Proceedings of International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116882309","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：