Pub Date : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000154
M. Toeroe
The paper presents a prototype tool developed for dimension server applications running on Jambala, Ericsson's cluster-based server platform. Its very high availability derives predominantly from software solutions in the underlying TelORB operating system. The prototype-dimensioning tool is based on a high level model of TelORB. It follows features of the operating system rather than a given application; therefore, it is applicable to any existing or new application developed for the platform. Thus, it can assist from the beginning application designers and site engineers in tuning the system for the best performance. According to the benchmark results, with the prototype tool, we achieved up to 95% precision for the simulated application. The prototype also demonstrated a significant flexibility facilitating quick evaluation of "what-if" scenarios. Although the presented model follows the TelORB design, we believe, it is easily adaptable to other computer clusters.
{"title":"Performance simulation of the Jambala platform","authors":"M. Toeroe","doi":"10.1109/SIMSYM.2002.1000154","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000154","url":null,"abstract":"The paper presents a prototype tool developed for dimension server applications running on Jambala, Ericsson's cluster-based server platform. Its very high availability derives predominantly from software solutions in the underlying TelORB operating system. The prototype-dimensioning tool is based on a high level model of TelORB. It follows features of the operating system rather than a given application; therefore, it is applicable to any existing or new application developed for the platform. Thus, it can assist from the beginning application designers and site engineers in tuning the system for the best performance. According to the benchmark results, with the prototype tool, we achieved up to 95% precision for the simulated application. The prototype also demonstrated a significant flexibility facilitating quick evaluation of \"what-if\" scenarios. Although the presented model follows the TelORB design, we believe, it is easily adaptable to other computer clusters.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128632096","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000087
Anush Kumar, L. F. Wilson, Thomas B. Stephens, J. Sucharitaves
Simulations often need access to physically distributed data resources such as datasets, sensors, or even other simulations. The Agent-Based Environment for Linking Simulations (ABELS) is a framework that allows distributed simulations and data resources to dynamically communicate with each other in real time to produce useful and accurate results. Specifically, it allows independently designed simulations to communicate with no a priori knowledge of the details of other simulations and data resources. The ABELS framework consists of user entities such as simulations and data resources, generic local agents that provide an interface to the system, and a brokering system that facilitates the dynamic linking of heterogeneous simulations and data sources. This paper presents the design and implementation of the ABELS brokering system and described its interactions with the generic local agents. The brokering system consists of a registration module, a lookup module, a communication facilitator, a resource manager, and a matchmaking module. Sun Microsystems' Jini technology is used to implement certain modules of the brokering system.
{"title":"The ABELS brokering system","authors":"Anush Kumar, L. F. Wilson, Thomas B. Stephens, J. Sucharitaves","doi":"10.1109/SIMSYM.2002.1000087","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000087","url":null,"abstract":"Simulations often need access to physically distributed data resources such as datasets, sensors, or even other simulations. The Agent-Based Environment for Linking Simulations (ABELS) is a framework that allows distributed simulations and data resources to dynamically communicate with each other in real time to produce useful and accurate results. Specifically, it allows independently designed simulations to communicate with no a priori knowledge of the details of other simulations and data resources. The ABELS framework consists of user entities such as simulations and data resources, generic local agents that provide an interface to the system, and a brokering system that facilitates the dynamic linking of heterogeneous simulations and data sources. This paper presents the design and implementation of the ABELS brokering system and described its interactions with the generic local agents. The brokering system consists of a registration module, a lookup module, a communication facilitator, a resource manager, and a matchmaking module. Sun Microsystems' Jini technology is used to implement certain modules of the brokering system.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121417004","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000082
D. E. Martin, P. Wilsey, R. Hoekstra, E. Keiter, S. Hutchinson, T. Russo, Lon J. Waters
The emergence of mixed-signal (analog and digital) integrated circuits motivates the need for CAD tools supporting mixed-signal design and analysis. Furthermore, the presence of a large body of existing models in existing modeling language and the need for modeling mixed-signal (analog and digital) circuits motivates the need for a single unified simulation framework into which different parallel simulation subsystems can be easily connected. In this paper we have review the design of a light-weight simulation backplane for integrating simulators from different domains. Of particular focus for this paper is the integration of a parallel SPICE (analog circuit) simulator called Xyce/sup TM/ with a parallel VHDL (digital circuit) simulator called SAVANT.
{"title":"Integrating multiple parallel simulation engines for mixed-technology parallel simulation","authors":"D. E. Martin, P. Wilsey, R. Hoekstra, E. Keiter, S. Hutchinson, T. Russo, Lon J. Waters","doi":"10.1109/SIMSYM.2002.1000082","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000082","url":null,"abstract":"The emergence of mixed-signal (analog and digital) integrated circuits motivates the need for CAD tools supporting mixed-signal design and analysis. Furthermore, the presence of a large body of existing models in existing modeling language and the need for modeling mixed-signal (analog and digital) circuits motivates the need for a single unified simulation framework into which different parallel simulation subsystems can be easily connected. In this paper we have review the design of a light-weight simulation backplane for integrating simulators from different domains. Of particular focus for this paper is the integration of a parallel SPICE (analog circuit) simulator called Xyce/sup TM/ with a parallel VHDL (digital circuit) simulator called SAVANT.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130086211","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000172
Chen Xiaoming, Hong Geok-Soon
Carrier Sense Media Access (CSMA) protocol is a widely used algorithm to control the access of a computer to the shared media (channel). There are several variants derived from this Media Access Control (MAC) method, such as non-persistent CSMA, 1-persistent CSMA, p-persistent CSMA, and CSMA/CD etc. These algorithms are successful in time-insensitive network, such as Ethernet. But for the fieldbus-based real-time control system that is time-sensitive, they are no longer adequate. To meet the real-time requirements, Echelon Corporation proposed a novel CSMA algorithm, the predictive p-persistent CSMA protocol. In this paper, we evaluate the performance of this protocol by a discrete-event simulation. A node-centric simulation model based on event-driven simulation language - SMPL - is designed using what we call "FSM-to-EVENT" method. Also, some techniques are presented to achieve this purpose. Finally, the experiments and results, including the comparison with other protocols, are described.
{"title":"A simulation study of the predictive p-persistent CSMA protocol","authors":"Chen Xiaoming, Hong Geok-Soon","doi":"10.1109/SIMSYM.2002.1000172","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000172","url":null,"abstract":"Carrier Sense Media Access (CSMA) protocol is a widely used algorithm to control the access of a computer to the shared media (channel). There are several variants derived from this Media Access Control (MAC) method, such as non-persistent CSMA, 1-persistent CSMA, p-persistent CSMA, and CSMA/CD etc. These algorithms are successful in time-insensitive network, such as Ethernet. But for the fieldbus-based real-time control system that is time-sensitive, they are no longer adequate. To meet the real-time requirements, Echelon Corporation proposed a novel CSMA algorithm, the predictive p-persistent CSMA protocol. In this paper, we evaluate the performance of this protocol by a discrete-event simulation. A node-centric simulation model based on event-driven simulation language - SMPL - is designed using what we call \"FSM-to-EVENT\" method. Also, some techniques are presented to achieve this purpose. Finally, the experiments and results, including the comparison with other protocols, are described.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130569916","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000145
H. D. S. Arons, C. A. Boer
It has been demonstrated that Arena simulation models can be parameterized and stored in a relational database for later use. In this way an Arena model can be uniquely described by assigning the right values to the corresponding parameters. These parameters contain detailed information concerning type and number of modules, entities and routes which entities follow through the system. A modeler could query such a database hoping that it would contain the Arena (sub)model that one has in mind. Unfortunately, an exact match will seldom occur but the database might contain one or more similar models. In earlier work a numerical algorithm was proposed resulting in a ranked list of simulation models in the database. According to this the lower a model is ranked the more it resembles the specified model. This model depends on a number of weight factors. In this paper the ranking algorithm is evaluated by carrying out a number of experiments.
{"title":"Ranking a list of discrete-event models","authors":"H. D. S. Arons, C. A. Boer","doi":"10.1109/SIMSYM.2002.1000145","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000145","url":null,"abstract":"It has been demonstrated that Arena simulation models can be parameterized and stored in a relational database for later use. In this way an Arena model can be uniquely described by assigning the right values to the corresponding parameters. These parameters contain detailed information concerning type and number of modules, entities and routes which entities follow through the system. A modeler could query such a database hoping that it would contain the Arena (sub)model that one has in mind. Unfortunately, an exact match will seldom occur but the database might contain one or more similar models. In earlier work a numerical algorithm was proposed resulting in a ranked list of simulation models in the database. According to this the lower a model is ranked the more it resembles the specified model. This model depends on a number of weight factors. In this paper the ranking algorithm is evaluated by carrying out a number of experiments.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114468965","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 : 2002-04-14DOI: 10.1109/SIMSYM.2002.1000076
H. Schwetman
Summary form only given, as follows. People have been dealing with complex systems since the dawn of time. They have tried to predict the weather, cure disease and interact with society, even in the most primitive of times. This talk argues that we (humans) have approached complex systems using a standard approach, utilizing the following steps: (1) collect data from (make observations of) the system, (2) create some useful abstractions of some features of the system, (3) develop a model of the system, and (4) use this model to try to predict future behavior of the system. Today, analysts use simulation models in exactly the same way. We observe the system, develop some abstractions, and then construct a simulation of the system. We then we use this model to make predictions about the future behavior of the system. The talk explores some earlier attempts at developing models. It then shows how simulation models are a natural outgrowth of these earlier models. The talk concludes with a discussion of tradeoffs associated with conducting systems analysis projects. The key question is: if this stuff is so good, why don't more people use it?
{"title":"Coping with complexity: abstractions, models and data","authors":"H. Schwetman","doi":"10.1109/SIMSYM.2002.1000076","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000076","url":null,"abstract":"Summary form only given, as follows. People have been dealing with complex systems since the dawn of time. They have tried to predict the weather, cure disease and interact with society, even in the most primitive of times. This talk argues that we (humans) have approached complex systems using a standard approach, utilizing the following steps: (1) collect data from (make observations of) the system, (2) create some useful abstractions of some features of the system, (3) develop a model of the system, and (4) use this model to try to predict future behavior of the system. Today, analysts use simulation models in exactly the same way. We observe the system, develop some abstractions, and then construct a simulation of the system. We then we use this model to make predictions about the future behavior of the system. The talk explores some earlier attempts at developing models. It then shows how simulation models are a natural outgrowth of these earlier models. The talk concludes with a discussion of tradeoffs associated with conducting systems analysis projects. The key question is: if this stuff is so good, why don't more people use it?","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129823017","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 : 1900-01-01DOI: 10.1109/SIMSYM.2002.1000075
The following topics are dealt with: network modeling and simulation; parallel and distributed simulation; simulation based performance analysis; simulation languages, tools, and environments; Web-based modeling and simulation; and simulation methodology and practices.
{"title":"Proceedings 35th Annual Simulation Symposium. SS 2002","authors":"","doi":"10.1109/SIMSYM.2002.1000075","DOIUrl":"https://doi.org/10.1109/SIMSYM.2002.1000075","url":null,"abstract":"The following topics are dealt with: network modeling and simulation; parallel and distributed simulation; simulation based performance analysis; simulation languages, tools, and environments; Web-based modeling and simulation; and simulation methodology and practices.","PeriodicalId":198576,"journal":{"name":"Proceedings 35th Annual Simulation Symposium. SS 2002","volume":"248 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131960194","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：