Wei Sun, Chen Yu, Yuanyuan Zhang, X. Défago, Y. Inoguchi
The scheduling of real-time tasks with fault-tolerant requirements has been an important problem in multiprocessor systems. Primary-backup (PB) approach is often used as a fault-tolerant technique to guarantee the deadlines of tasks despite the presence of faults. In this paper we propose a PB-based task scheduling approach, wherein an allocation parameter is used to search the available time slots for a newly arriving task, and the previously scheduled tasks can be rescheduled when there is no available time slot for the newly arriving task. In order to improve the schedulability we extend the existing PB-overloading and the Backup-backup (BB) overloading. Our proposed task scheduling algorithm is compared with some existing scheduling algorithms in the literature through simulation studies. The results have shown that the task rejection ratio of our real-time task scheduling algorithm is lower than the compared algorithms.
{"title":"Real-time Task Scheduling Using Extended Overloading Technique for Multiprocessor Systems","authors":"Wei Sun, Chen Yu, Yuanyuan Zhang, X. Défago, Y. Inoguchi","doi":"10.1109/DS-RT.2007.38","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.38","url":null,"abstract":"The scheduling of real-time tasks with fault-tolerant requirements has been an important problem in multiprocessor systems. Primary-backup (PB) approach is often used as a fault-tolerant technique to guarantee the deadlines of tasks despite the presence of faults. In this paper we propose a PB-based task scheduling approach, wherein an allocation parameter is used to search the available time slots for a newly arriving task, and the previously scheduled tasks can be rescheduled when there is no available time slot for the newly arriving task. In order to improve the schedulability we extend the existing PB-overloading and the Backup-backup (BB) overloading. Our proposed task scheduling algorithm is compared with some existing scheduling algorithms in the literature through simulation studies. The results have shown that the task rejection ratio of our real-time task scheduling algorithm is lower than the compared algorithms.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125534272","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}
This paper presents a framework for modelling emotionally driven, context aware crowd behaviour in real time. It explores a scalable approach for applying dynamic drives to the behaviour of the crowd members, allowing their agendas to be changed according to context. A survey of previous work on crowd modelling, emotion modelling and large-scale multi-agent systems leads to the definition of a conceptual framework, which is applied to a prototype system for building the agendas of people in a railway station environment. The system is evaluated by varying the emotional drives, to assess the impact on agenda-building, and tested for real-time performance, in order to evaluate the scalability of the framework.
{"title":"A Conceptual Framework for Modelling Crowd Behaviour","authors":"P. Dey, D. Roberts","doi":"10.1109/DS-RT.2007.5","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.5","url":null,"abstract":"This paper presents a framework for modelling emotionally driven, context aware crowd behaviour in real time. It explores a scalable approach for applying dynamic drives to the behaviour of the crowd members, allowing their agendas to be changed according to context. A survey of previous work on crowd modelling, emotion modelling and large-scale multi-agent systems leads to the definition of a conceptual framework, which is applied to a prototype system for building the agendas of people in a railway station environment. The system is evaluated by varying the emotional drives, to assess the impact on agenda-building, and tested for real-time performance, in order to evaluate the scalability of the framework.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123643772","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}
Distributed simulations that support a massive number of users typically divide the virtual world into zones that are managed by separate servers to evenly distribute resources and achieve scalability. However, such zoning restricts cross-zonal interactions and exposes the division of the world to the participating parties. Problems such as crowding one zone among others defeats the very purpose of interest management and makes geographic partitioning inefficient for modeling interactions. In this work, we have designed and implemented a visibility-driven approach to make the partitioning transparent to users. The effectiveness of this distributed architecture is tested through a prototype implementation. We also introduce a novel idea to dynamic load balancing that can be achieved in real-time without modifying the communication architecture. By increasing the granularity of the partitioning and providing a layered approach to zoning, transient crowding can be handled by adoptively dispersing parts of the crowded zone to adjacent servers.
{"title":"A Visibility-Driven Approach to Managing Interest in Distributed Simulations with Dynamic Load Balancing","authors":"Ihab Kazem, D. Ahmed, S. Shirmohammadi","doi":"10.1109/DS-RT.2007.11","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.11","url":null,"abstract":"Distributed simulations that support a massive number of users typically divide the virtual world into zones that are managed by separate servers to evenly distribute resources and achieve scalability. However, such zoning restricts cross-zonal interactions and exposes the division of the world to the participating parties. Problems such as crowding one zone among others defeats the very purpose of interest management and makes geographic partitioning inefficient for modeling interactions. In this work, we have designed and implemented a visibility-driven approach to make the partitioning transparent to users. The effectiveness of this distributed architecture is tested through a prototype implementation. We also introduce a novel idea to dynamic load balancing that can be achieved in real-time without modifying the communication architecture. By increasing the granularity of the partitioning and providing a layered approach to zoning, transient crowding can be handled by adoptively dispersing parts of the crowded zone to adjacent servers.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128106442","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}
The presentation addresse the issue of spatially constrained spontaneous interaction among digital artefacts. An explicit model for spatial proximity is investigated based on geometric descriptions of "zones of influence" (ZoI) of artefacts, enabling the triggering of their interactions based on real time verification of relations among Zols (intersection, inclusion).
{"title":"Spatial Awareness of Digital Artefacts","authors":"A. Ferscha","doi":"10.1109/DS-RT.2007.41","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.41","url":null,"abstract":"The presentation addresse the issue of spatially constrained spontaneous interaction among digital artefacts. An explicit model for spatial proximity is investigated based on geometric descriptions of \"zones of influence\" (ZoI) of artefacts, enabling the triggering of their interactions based on real time verification of relations among Zols (intersection, inclusion).","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"86 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131770570","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}
State management is a fundamental requirement of multi-user applications like distributed simulations or networked games. The quality of the experience of such applications heavily depends on synchronous communication. The movement of an entity from one logical zone into another initiates reorganization of the peer-to-peer structure and eventually ruins synchronous interactions. The frequent nature of such event in the distributed simulations has significant impact on the performance and cannot be ignored. In this paper, we present a performance enhancement mechanism considering the physical attributes of the entities. We demonstrate that clustering the entities based on their physical characteristics or behavior significantly reduces peer- to-peer structural reformation penalties. The effectiveness of such clustering mechanism is simulated and analyzed in the context MMOG.
{"title":"Performance Enhancement in MMOGs Using Entity Types","authors":"D. Ahmed, S. Shirmohammadi, J. Oliveira","doi":"10.1109/DS-RT.2007.35","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.35","url":null,"abstract":"State management is a fundamental requirement of multi-user applications like distributed simulations or networked games. The quality of the experience of such applications heavily depends on synchronous communication. The movement of an entity from one logical zone into another initiates reorganization of the peer-to-peer structure and eventually ruins synchronous interactions. The frequent nature of such event in the distributed simulations has significant impact on the performance and cannot be ignored. In this paper, we present a performance enhancement mechanism considering the physical attributes of the entities. We demonstrate that clustering the entities based on their physical characteristics or behavior significantly reduces peer- to-peer structural reformation penalties. The effectiveness of such clustering mechanism is simulated and analyzed in the context MMOG.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122935313","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}
We formulate the real-time routing problem in static multi-hop wireless networks as an optimization problem, whose solution is the optimal routes relative to an end- to-end delay based objective. The problem is formulated as a mixed integer linear program. The variance of the delay with respect to the aggregate interference measures is empirically studied and a linear approximation is proposed. We show that this formulation yields routes that significantly outperform the best routes obtained by OLSR. Finally, we discuss the applications of such a model both in terms of capacity analysis, on-line algorithms for static scenarios, and extensions to allow the development of distributed protocols that solve the optimization problem.
{"title":"Towards Interference-Aware Routing for Real-time Traffic in Multi-hop Wireless Networks","authors":"Vinay Kolar, N. Abu-Ghazaleh","doi":"10.1109/DS-RT.2007.44","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.44","url":null,"abstract":"We formulate the real-time routing problem in static multi-hop wireless networks as an optimization problem, whose solution is the optimal routes relative to an end- to-end delay based objective. The problem is formulated as a mixed integer linear program. The variance of the delay with respect to the aggregate interference measures is empirically studied and a linear approximation is proposed. We show that this formulation yields routes that significantly outperform the best routes obtained by OLSR. Finally, we discuss the applications of such a model both in terms of capacity analysis, on-line algorithms for static scenarios, and extensions to allow the development of distributed protocols that solve the optimization problem.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126434951","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}
The partitioning constitutes one of the basic problems that need to be handled in distributed virtual environments for maintaining consistency among users' view of the virtual scene and for optimizing the performance of the system. This paper presents an approach for handling the partitioning problem, which is based on objects' attributes. In particular, the approach proposes a technique, which takes into account the degree of interaction that the objects of the virtual environment carry for predicting future avatar behavior. This prediction of avatars' behavior based on objects ' attributes defines the initial partitioning of the virtual space.
{"title":"Partitioning of Distributed Virtual Environments Based on Objects' Attributes","authors":"C. Bouras, E. Giannaka, T. Tsiatsos","doi":"10.1109/DS-RT.2007.34","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.34","url":null,"abstract":"The partitioning constitutes one of the basic problems that need to be handled in distributed virtual environments for maintaining consistency among users' view of the virtual scene and for optimizing the performance of the system. This paper presents an approach for handling the partitioning problem, which is based on objects' attributes. In particular, the approach proposes a technique, which takes into account the degree of interaction that the objects of the virtual environment carry for predicting future avatar behavior. This prediction of avatars' behavior based on objects ' attributes defines the initial partitioning of the virtual space.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116678914","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}
A. Ozaki, Masashi Shiraishi, H. Sato, Kazutaka Matsushita, S. Watanabe, M. Furuichi
We have already proposed DTSS (event aware Dynamic Time Step Synchronization method) for speeding up moving objects (MOs) simulation, e.g. aircraft, ships, vehicles and so on, and evaluated it on the HLA (High Level Architecture, IEEE1516) computer cluster environment. However, speeding up the simulation for a number of MOs on a single processor is required as well, when the size of the problem is increased. In this paper, we propose DTSS- RT (DTSS for Road Traffic simulation) that can speed up the simulation by reducing the simulation cost of each MO and the synchronization cost between MOs without degrading simulation accuracy. For evaluating DTSS-RT, we employed a road traffic sub-simulator of RoboCup rescue simulation. The results show that the performance of the simulation based on DTSS-RT is improved approximately 2 to 3 times over that of the conventional method except when the situation includes a heavy traffic jam.
{"title":"High Performance Road Traffic Simulation based on Dynamic Time Step Synchronization Method","authors":"A. Ozaki, Masashi Shiraishi, H. Sato, Kazutaka Matsushita, S. Watanabe, M. Furuichi","doi":"10.1109/DS-RT.2007.30","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.30","url":null,"abstract":"We have already proposed DTSS (event aware Dynamic Time Step Synchronization method) for speeding up moving objects (MOs) simulation, e.g. aircraft, ships, vehicles and so on, and evaluated it on the HLA (High Level Architecture, IEEE1516) computer cluster environment. However, speeding up the simulation for a number of MOs on a single processor is required as well, when the size of the problem is increased. In this paper, we propose DTSS- RT (DTSS for Road Traffic simulation) that can speed up the simulation by reducing the simulation cost of each MO and the synchronization cost between MOs without degrading simulation accuracy. For evaluating DTSS-RT, we employed a road traffic sub-simulator of RoboCup rescue simulation. The results show that the performance of the simulation based on DTSS-RT is improved approximately 2 to 3 times over that of the conventional method except when the situation includes a heavy traffic jam.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131066297","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}
The goal of this paper is to provide an optimal solution for data distribution management (DDM) in large-scale distributed simulations. Until now, all existing DDM approaches have tried to make DDM more efficient in different ways; however, none has been able to optimize performance. The main reason for this inability is that these approaches manipulate the data generated in a simulation without evaluating the size of it. We propose a novel resource allocation scheme, the adaptive resource allocation control scheme (ARAC). The ARAC scheme is designed to optimize resource allocations for local and distributed processing work at each federate according to the size of the simulation. Efficiency is achieved by applying the analysis results of a static probability model, which we call the matching model. Performance comparisons between the existing grid-based approaches and the new adaptive approach show that the new scheme is much more flexible in adapting to various simulation sizes and comes much closer to an optimal solution. The novelty of the ARAC scheme is that it is able to scale the size of a simulation and control the simulation itself by running it in the most appropriate mode to achieve the desired efficiency. As a final result, the optimum performance is best approached.
{"title":"An Adaptive Resource Allocation Scheme for Large-scale Distributed Simulation System","authors":"A. Boukerche, YunFeng Gu","doi":"10.1109/DS-RT.2007.12","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.12","url":null,"abstract":"The goal of this paper is to provide an optimal solution for data distribution management (DDM) in large-scale distributed simulations. Until now, all existing DDM approaches have tried to make DDM more efficient in different ways; however, none has been able to optimize performance. The main reason for this inability is that these approaches manipulate the data generated in a simulation without evaluating the size of it. We propose a novel resource allocation scheme, the adaptive resource allocation control scheme (ARAC). The ARAC scheme is designed to optimize resource allocations for local and distributed processing work at each federate according to the size of the simulation. Efficiency is achieved by applying the analysis results of a static probability model, which we call the matching model. Performance comparisons between the existing grid-based approaches and the new adaptive approach show that the new scheme is much more flexible in adapting to various simulation sizes and comes much closer to an optimal solution. The novelty of the ARAC scheme is that it is able to scale the size of a simulation and control the simulation itself by running it in the most appropriate mode to achieve the desired efficiency. As a final result, the optimum performance is best approached.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129016160","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}
In a surveillance mission, the task of Unmanned Aerial Vehicles (UAV) path planning can in some cases be addressed using Sequential Monte Carlo (SMC) simulation. If sufficient a priori information about the target and the environment is available an assessment of the future state of the target is obtained by the SMC simulation. This assessment is used in a set of "what-if" simulations to compare different alternative UAV paths. In a static environment this simulation can be conducted prior to the mission. However, if the environment is dynamic, it is required to run the "what-if" simulations on-line i.e. in real-time. In this paper the details of this on-line simulation approach in UAV path planning is studied and its performance is compared with two other methods: an off-line simulationaided path planning and an exhaustive search method. The conducted simulations indicate that the on-line simulation has generally a higher performance compared with the two other methods.
{"title":"Using On-line Simulation for Adaptive Path Planning of UAVs","authors":"Farzad Kamrani, R. Ayani","doi":"10.1109/DS-RT.2007.45","DOIUrl":"https://doi.org/10.1109/DS-RT.2007.45","url":null,"abstract":"In a surveillance mission, the task of Unmanned Aerial Vehicles (UAV) path planning can in some cases be addressed using Sequential Monte Carlo (SMC) simulation. If sufficient a priori information about the target and the environment is available an assessment of the future state of the target is obtained by the SMC simulation. This assessment is used in a set of \"what-if\" simulations to compare different alternative UAV paths. In a static environment this simulation can be conducted prior to the mission. However, if the environment is dynamic, it is required to run the \"what-if\" simulations on-line i.e. in real-time. In this paper the details of this on-line simulation approach in UAV path planning is studied and its performance is compared with two other methods: an off-line simulationaided path planning and an exhaustive search method. The conducted simulations indicate that the on-line simulation has generally a higher performance compared with the two other methods.","PeriodicalId":266467,"journal":{"name":"11th IEEE International Symposium on Distributed Simulation and Real-Time Applications (DS-RT'07)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128559998","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：