Pub Date : 2008-06-11DOI: 10.1109/SIES.2008.4577679
Anders Sejer Tranberg-Hansen, J. Madsen, Bjørn Sand Jensen
This paper presents an abstract service based estimation method for MPSoC performance modelling which allows fast, cycle accurate design space exploration of complex architectures including multi processor configurations at a very early stage in the design phase. The modelling method uses a service oriented model of computation based on Hierarchical Colored Petri Nets and allows the modelling of both software and hardware in one unified model. To illustrate the potential of the method, a small MPSoC system, developed at Bang & Olufsen ICEpower a/s, is modelled and performance estimates are produced for various configurations of the system in order to explore the best possible implementation.
{"title":"A service based estimation method for MPSoC performance modelling","authors":"Anders Sejer Tranberg-Hansen, J. Madsen, Bjørn Sand Jensen","doi":"10.1109/SIES.2008.4577679","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577679","url":null,"abstract":"This paper presents an abstract service based estimation method for MPSoC performance modelling which allows fast, cycle accurate design space exploration of complex architectures including multi processor configurations at a very early stage in the design phase. The modelling method uses a service oriented model of computation based on Hierarchical Colored Petri Nets and allows the modelling of both software and hardware in one unified model. To illustrate the potential of the method, a small MPSoC system, developed at Bang & Olufsen ICEpower a/s, is modelled and performance estimates are produced for various configurations of the system in order to explore the best possible implementation.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122356086","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577709
T. Reinbacher, Martin Kramer, M. Horauer, Bastian Schlich
Model checking is considered a promising approach for the verification of software for embedded systems. Generating system models that are close to real-life behavior, however, is challenging. As a result, in some approaches a model can be automatically constructed out of the assembly code along with an appropriate target simulator/debugger. The implementation of the latter is crucial for the entire verification process. To that end, this paper presents requirements and challenges that arise when implementing and verifying such a simulator for the [mc]square model checker from the RWTH Aachen University.
{"title":"Challenges in embedded model checking — a simulator for the [mc]square model checker","authors":"T. Reinbacher, Martin Kramer, M. Horauer, Bastian Schlich","doi":"10.1109/SIES.2008.4577709","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577709","url":null,"abstract":"Model checking is considered a promising approach for the verification of software for embedded systems. Generating system models that are close to real-life behavior, however, is challenging. As a result, in some approaches a model can be automatically constructed out of the assembly code along with an appropriate target simulator/debugger. The implementation of the latter is crucial for the entire verification process. To that end, this paper presents requirements and challenges that arise when implementing and verifying such a simulator for the [mc]square model checker from the RWTH Aachen University.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115027898","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577691
Thi-Quynh Bui, O. Aktouf, M. Dang
Component-based software development paradigm enables the construction of complex applications by assembling existing self-contained components. The cost of the software development process can then be sharply reduced. Current software systems are becoming more distributed and operate in highly dynamic environments. Therefore, dependability of component-based applications is an important research issue. In this paper, we propose a diagnosis service architecture that enhances dependability of component-based applications, especially embedded ones. This diagnosis service provides the ability of detection and location of faulty components during runtime system execution. As far as we know it is the first work that applies system-level diagnosis in embedded software component based applications for increasing the reliability of the whole system.
{"title":"Software component diagnosis service: architecture description","authors":"Thi-Quynh Bui, O. Aktouf, M. Dang","doi":"10.1109/SIES.2008.4577691","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577691","url":null,"abstract":"Component-based software development paradigm enables the construction of complex applications by assembling existing self-contained components. The cost of the software development process can then be sharply reduced. Current software systems are becoming more distributed and operate in highly dynamic environments. Therefore, dependability of component-based applications is an important research issue. In this paper, we propose a diagnosis service architecture that enhances dependability of component-based applications, especially embedded ones. This diagnosis service provides the ability of detection and location of faulty components during runtime system execution. As far as we know it is the first work that applies system-level diagnosis in embedded software component based applications for increasing the reliability of the whole system.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115519058","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577703
Benoît Badrignans, R. Elbaz, L. Torres
Remote update of hardware systems is a convenient service enabled by Field Programmable Gate Arrays (FPGA) based systems. This service turns out to be essential in applications like Space-based FPGA systems or Set-top Boxes. However, the remote characteristic allows for a set of attacks that may challenge the confidentiality and the integrity of the FPGA configuration, the bitstream. Existing schemes propose to encrypt and to authenticate the bitstream to thwart those attacks. However we show in this paper that they do not prevent the replay of old bitstream versions, and thus give the opportunity to an adversary to downgrade the system. We propose a new technique that ensures bitstream confidentiality and integrity and detects replay of old bitstreams.
{"title":"Secure update Mechanism for Remote Update of FPGA-Based System","authors":"Benoît Badrignans, R. Elbaz, L. Torres","doi":"10.1109/SIES.2008.4577703","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577703","url":null,"abstract":"Remote update of hardware systems is a convenient service enabled by Field Programmable Gate Arrays (FPGA) based systems. This service turns out to be essential in applications like Space-based FPGA systems or Set-top Boxes. However, the remote characteristic allows for a set of attacks that may challenge the confidentiality and the integrity of the FPGA configuration, the bitstream. Existing schemes propose to encrypt and to authenticate the bitstream to thwart those attacks. However we show in this paper that they do not prevent the replay of old bitstream versions, and thus give the opportunity to an adversary to downgrade the system. We propose a new technique that ensures bitstream confidentiality and integrity and detects replay of old bitstreams.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115893389","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577698
M. Jonsson, Kristina Kunert
This paper presents a framework for how to use ARQ (automatic repeat request) in combination with real-time worst-case scheduling analysis to be able to support reliable hard real-time communication. We show how to handle retransmissions of erroneous data packets, while still not jeopardizing stated delay guarantees of other packets. We demonstrate this by taking a point-to-point link as an example. Through our simulation studies we have shown that a reduction of the message error rate by several orders of magnitude is possible with a reasonable utilization penalty.
{"title":"Reliable hard real-time communication in industrial and embedded systems","authors":"M. Jonsson, Kristina Kunert","doi":"10.1109/SIES.2008.4577698","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577698","url":null,"abstract":"This paper presents a framework for how to use ARQ (automatic repeat request) in combination with real-time worst-case scheduling analysis to be able to support reliable hard real-time communication. We show how to handle retransmissions of erroneous data packets, while still not jeopardizing stated delay guarantees of other packets. We demonstrate this by taking a point-to-point link as an example. Through our simulation studies we have shown that a reduction of the message error rate by several orders of magnitude is possible with a reasonable utilization penalty.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126329254","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577694
Hongbin Li, Luís Almeida, Fausto Carramate, Zhi Wang, Youxian Sun
The research presented in this paper addresses the issue of distributed motion control for keeping certain degree of wireless connectivity among mobile units. In our approach, each mobile unit is equipped with an omnidirectional antenna that communicates at 2.4 GHz (IEEE 802.15.4). We first propose a framework for connectivity tracking and computation of relative positions. Then, based on the generated relative positions, a motion control strategy is presented aiming at maintaining a required level of connectivity among mobile units. We implemented the proposed framework on IEEE 802.15.4 based nodes and validated the idea of generating connectivity-aware relative positions. A set of simulation and experimental results are shown that illustrate the effectiveness of the motion control strategy.
{"title":"Connectivity-aware motion control among autonomous mobile units","authors":"Hongbin Li, Luís Almeida, Fausto Carramate, Zhi Wang, Youxian Sun","doi":"10.1109/SIES.2008.4577694","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577694","url":null,"abstract":"The research presented in this paper addresses the issue of distributed motion control for keeping certain degree of wireless connectivity among mobile units. In our approach, each mobile unit is equipped with an omnidirectional antenna that communicates at 2.4 GHz (IEEE 802.15.4). We first propose a framework for connectivity tracking and computation of relative positions. Then, based on the generated relative positions, a motion control strategy is presented aiming at maintaining a required level of connectivity among mobile units. We implemented the proposed framework on IEEE 802.15.4 based nodes and validated the idea of generating connectivity-aware relative positions. A set of simulation and experimental results are shown that illustrate the effectiveness of the motion control strategy.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125321141","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577702
J. R. Millán-Almaraz, R. Romero-Troncoso, L. M. Contreras-Medina, A. García-Perez
Preventive maintenance on machinery is one of the major concerns in industry. Induction motors represent 85% of the total power consumption in the world and several faults related to these motors that increase the power consumption are not easily detected; therefore, periodic fault monitoring is mandatory. There are several techniques for fault detection in induction motors being current analysis the most popular among others. This techniques are focused on the analysis of induction motors that are directly fed by the line and do not consider the induced effects due to speed drives. The novelty of this research is the proposal of a new technique, based on discrete wavelet transform for transient analysis at the motor start, for broken rotor bar detection on induction motors fed in both: directly and with speed drive. The contribution of the present work is the development of a field programmable gate array embedded system implementation of a broken rotor bar on-line monitoring system for a low cost embedded system approach. Results from experimentation show the overall system performance. It is demonstrated that the proposed methodology is efficient to detect the motor faults when directly or speed drive fed.
{"title":"Embedded FPGA based induction motor monitoring system with speed drive fed using multiple wavelet analysis","authors":"J. R. Millán-Almaraz, R. Romero-Troncoso, L. M. Contreras-Medina, A. García-Perez","doi":"10.1109/SIES.2008.4577702","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577702","url":null,"abstract":"Preventive maintenance on machinery is one of the major concerns in industry. Induction motors represent 85% of the total power consumption in the world and several faults related to these motors that increase the power consumption are not easily detected; therefore, periodic fault monitoring is mandatory. There are several techniques for fault detection in induction motors being current analysis the most popular among others. This techniques are focused on the analysis of induction motors that are directly fed by the line and do not consider the induced effects due to speed drives. The novelty of this research is the proposal of a new technique, based on discrete wavelet transform for transient analysis at the motor start, for broken rotor bar detection on induction motors fed in both: directly and with speed drive. The contribution of the present work is the development of a field programmable gate array embedded system implementation of a broken rotor bar on-line monitoring system for a low cost embedded system approach. Results from experimentation show the overall system performance. It is demonstrated that the proposed methodology is efficient to detect the motor faults when directly or speed drive fed.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126964058","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577700
Paul Milbredt, M. Horauer, A. Steininger
Distributed, time-triggered communication based on FlexRay is likely to become an enabler for future safety related applications in the automotive domain. Prior to series deployment, however, confidence has to be established that all mechanisms work as expected. One particular issue in this regard is the clique problem. Cliques are groups of nodes connected to the same bus which are only able to communicate with the members of the same clique, but not with members from another one. In time-triggered systems cliques might be caused, for instance, by Byzantine faults leading to a different view of the global time. In constrast to other hard real-time systems, FlexRay lacks explicit protocol support for detecting and resolving cliques. Thus, in this paper we investigate the clique problem in a real FlexRay system. We explain the different types of cliques and give examples how they might emerge and look like. One focus is the experimental study of the behavior of a real FlexRay cluster with existing cliques. In particular, we investigate the integration behavior of nodes into a system with present cliques as well as the behavior of the system when it is in a clique state. After a presentation of the results, we conclude by giving some directions about some protocol features which might be used for implementing clique avoidance or clique detection mechanisms.
{"title":"An investigation of the clique problem in FlexRay","authors":"Paul Milbredt, M. Horauer, A. Steininger","doi":"10.1109/SIES.2008.4577700","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577700","url":null,"abstract":"Distributed, time-triggered communication based on FlexRay is likely to become an enabler for future safety related applications in the automotive domain. Prior to series deployment, however, confidence has to be established that all mechanisms work as expected. One particular issue in this regard is the clique problem. Cliques are groups of nodes connected to the same bus which are only able to communicate with the members of the same clique, but not with members from another one. In time-triggered systems cliques might be caused, for instance, by Byzantine faults leading to a different view of the global time. In constrast to other hard real-time systems, FlexRay lacks explicit protocol support for detecting and resolving cliques. Thus, in this paper we investigate the clique problem in a real FlexRay system. We explain the different types of cliques and give examples how they might emerge and look like. One focus is the experimental study of the behavior of a real FlexRay cluster with existing cliques. In particular, we investigate the integration behavior of nodes into a system with present cliques as well as the behavior of the system when it is in a clique state. After a presentation of the results, we conclude by giving some directions about some protocol features which might be used for implementing clique avoidance or clique detection mechanisms.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130153135","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577695
T. Sivanthi, U. Killat
The need to support future requirements necessitates adding flexibility into the design of a distributed real-time embedded system. The added flexibility allows the system to adapt to the future requirements at a minimal cost. This design flexibility is a qualitative attribute which lacks a quantitative measure to evaluate the different designs of a distributed real-time embedded system. In this paper, we suggest a way to quantify the design flexibility of a distributed real-time embedded system using an economic measure. We maximize this measure using a formal framework to derive an optimal flexible design which accommodates the evolving requirements at a minimal cost.
{"title":"Valuing the design flexibility of a distributed real-time embedded system","authors":"T. Sivanthi, U. Killat","doi":"10.1109/SIES.2008.4577695","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577695","url":null,"abstract":"The need to support future requirements necessitates adding flexibility into the design of a distributed real-time embedded system. The added flexibility allows the system to adapt to the future requirements at a minimal cost. This design flexibility is a qualitative attribute which lacks a quantitative measure to evaluate the different designs of a distributed real-time embedded system. In this paper, we suggest a way to quantify the design flexibility of a distributed real-time embedded system using an economic measure. We maximize this measure using a formal framework to derive an optimal flexible design which accommodates the evolving requirements at a minimal cost.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130844478","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 : 2008-06-11DOI: 10.1109/SIES.2008.4577713
Stefan Grösbrink, Timo Kerstan
Modern embedded systems are composed of hard real-time tasks, soft real-time tasks and even non real-time tasks. A key requirement for system reliability is inter-task memory protection to prevent the spreading of faults across address spaces. Due to the lack of suitable approaches to enable virtual memory under hard real-time constraints and to support high flexibility for soft and non real-time tasks, we propose a modular page table approach with dynamic TLB partitioning. Different tasks are handled variably, depending on their real time constraints.
{"title":"Modular paging with dynamic TLB partitioning for embedded real-time systems","authors":"Stefan Grösbrink, Timo Kerstan","doi":"10.1109/SIES.2008.4577713","DOIUrl":"https://doi.org/10.1109/SIES.2008.4577713","url":null,"abstract":"Modern embedded systems are composed of hard real-time tasks, soft real-time tasks and even non real-time tasks. A key requirement for system reliability is inter-task memory protection to prevent the spreading of faults across address spaces. Due to the lack of suitable approaches to enable virtual memory under hard real-time constraints and to support high flexibility for soft and non real-time tasks, we propose a modular page table approach with dynamic TLB partitioning. Different tasks are handled variably, depending on their real time constraints.","PeriodicalId":438401,"journal":{"name":"2008 International Symposium on Industrial Embedded Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122012320","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：