DOCSLIB.ORG

Rapid Prototyping Suite of IEEE 802.15.4-Compliant Sensor Networks

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Rapid Prototyping Suite of IEEE 802.15.4-Compliant Sensor Networks Rapid prototyping suite of IEEE 802.15.4-compliant Sensor Networks Mangesh Chitnis1, Paolo Gai2, Giuseppe Lipari1, Paolo Pagano1, and Antonio Romano1 1Scuola Superiore Sant’Anna 2Evidence s.r.l. Piazza Martiri della liberta,` 33 Via Moruzzi, 1 56127 Pisa (I) 56124 Pisa (I) {m.chitnis, lipari, p.pagano, a.romano}@sssup.it [email protected] Abstract amount of computation in real-time. The rate at which data must be sampled is higher than typical WSNs application This paper presents a toolsuite for rapid prototyping and for environmental monitoring. For example, the sampling implementation of real-time applications on Wireless Sen- rate of a sensor can go up to hundreds of Hz. Also, many sor Networks. The work is motivated by the need to use tasks may need to be executed concurrently. For example, WSNs in industrial control contexts, where the sampling we may have tasks for data filtering, actuation, diagnos- rate, the workload is much higher than typical current ap- tic, logging, communication, etc. In practice, the compu- plications of WSNs, and the real-time constraints are much tational load on each node (in terms of amount of process- tighter. We present a simulator for early evaluation of ing time needed by the application tasks) may become rel- the real-time behavior of a WSN application; and a real- evant. In addition, such applications exhibit real-time con- time operating system that implement appropriate real-time straints, sometimes hard real-time ones. Many activities, scheduling policies to allow timing analysis and guarantee like sampling and actuation, must be triggered periodically timing constraints. We provide a demo based on a simple and executed with bounded response time, and late sensor but realistic network scenario showing that simulation is in messages may not be considered acceptable, otherwise the agreement with experimental results. system may not work properly. In a real-time system, it is important to guarantee system 1 Introduction predictability. The designer must check at system design time that the timing constraints will be respected under all conditions. A schedulability analysis for real-time applica- Many companies have recently started to consider the tions must be performed to guarantee that the system will use of Wireless Sensor Networks (WSN) in industrial au- work properly under worst-case load conditions. tomation systems and process control. The most urging mo- Unfortunately, the use of proper real-time mechanisms tivation is the need to reduce the amount of physical wires in in WSNs has not been deeply investigated until now. While a industrial plant. Reducing cables can significantly reduce few real-time Operating Systems have been proposed in the the cost for building and maintaining the system. Moreover, research literature and in the commercial market, TinyOS with less cables it is easier to dynamically reconfigure the is by large the most popular Operating System for WSN. machines, and implement plug-and-play components. An Unfortunately, TinyOS does not support predictable real- example of research effort in this sense is the the RI-MACS time scheduling policies. At the network level, mechanisms project [5], whose goal is to increase reconfigurability and for real-time communication and Quality of Service (QoS) adaptiveness of industrial automation platforms by using control (like the Collision Free Period access included in WSNs in selected cases. In the context of RI-MACS, we IEEE 802.15.4 standard[3]) are not implemented. But most are investigating the possibility to use WSNs for process importantly, what is missing is a proper comparative study control and configuration. and evaluation of the impact that various communication However, the requirements of these systems are substan- protocols and Operating System policies have on the real- tially different from those of other domains of WSNs. In time behavior of the system. addition to requirements for increased robustness and fault Another problem concerns the lack of proper simulation tolerance, each node is expected to perform a substantial tools. Simulation plays an important role both for research 1-4244-1455-5/07/$25.00 c 2007 IEEE. and for industrial practice. In academic research, simula- tion is a fundamental tool to compare different algorithms The Operating System puts these tasks into the Running and protocols, and to assess the performance of proposed status following the scheduling policy selected at the time solutions on complex realistic settings. In industrial design, when RT-App is instantiated. it is important to simulate the system before deployment for Because of the adopted scheduling algorithm, the tasks early assesment of performance, for system dimensioning, can be delayed by some time from the activation. In the case and to identify potential bottlenecks and problems. of a priority-based scheduler like FP, the preemption of the CPU depends on the difference in priority between the run- 2 The rapid prototyping suite ning task and the one which has been suddenly activated. In a scheduler based on activation times, the tasks are queued We propose to the community under GPL license: up and executed in FIFO order. In the latter case, the user • the RTNS [6] package, able to model and simulate, is not asked to specify a priority ad the delays are strongly not only the functional but also the temporal behavior, dependent on the load of the node. both at the network level and at the CPU level; RTNS can simulate single and multi-hop communica- tions for all the network topologies defined in the IEEE • the Erika Enterprise [2] Operating System customized 802.15.4 standard. The MAC and Physical layers of the for Wireless Sensor Network. Network Stack are natively simulated by NS-2 and RTNS only wraps these services into tasks handled by RT-App. Together these tools play the role of a rapid protyping suite, permitting to simulate and test in real hardware a va- 2.2 The Operating System riety of protocols and distributed applications suitable for real-time operations of WSN. The OS counterpart in this prototyping suite is ERIKA Enterprise (EE) commercialized by Evidence srl. EE con- 2.1 The simulator sists of a single and multi-processor real-time OS ker- nel implementing a collection of APIs similar to those of The RTNS simulator is a combination of the popular NS- OSEK/VDX standard for automotive embedded controllers. 2 package [4] for network protocol simulation, and of RT- It implements a shared memory model for a layered archi- Sim [7] for Real-Time OS (RTOS) simulation. Thanks to tecture composed by a substrate Kernel acting on a Hard- our simulator, it is possible to model the real-time tasks run- ware Abstraction Layer (HAL) dependent on the specific ning on each node, with their priority, execution time, and a platform. A set of software modules implements the task high-level pseudo-code modelling their functional behavior, management and the scheduling policy. and the network protocol used for communication between It is well suited to respond to the stringent pre-requisites nodes. In this way, it is possible to model end-to-end activi- of Wireless Sensor Networks, because of: ties, and measure the delay in transferring data from sensor to destination. • the minimal footprint in terms of RAM (about 3 The RTNS allows to simulate the networking aspects via KBytes), partially dependent on the hardware platform NS-2 as well as the real-time Operating Systems aspects and the adopted configuration; via RTSim. In NS-2, protocols are implemented as Agents: • the hard real-time compliance, because it complements any class that implements a protocol has to extend the Agent FP scheduling providing support for Immediate Prior- class. Instances of an agent class are the endpoints of wired ity Ceiling and Preemption Thresholds on single CPU and wireless connections. They are identified by INET ad- systems; dress and port and are the lowest layer able to pack and inject messages into the network. Application code is mod- • the supported Atmel AVR 5 architecture, very popular eled by the Application class. Applications use agents to in WSN contexts; send and receive messages. To simulate the behavior of the Operating System run- • the application layer customizable to fit diversified sce- ning on a node we construct an NS-2 Application called narios where WSN are deployed. RT-App abstracting all the features of a Real-Time Kernel. To implement the Network Stack substrate we adapted The simulator creates an instance of RT-App for each node, the libraries provided by Atmel[1] and compliant with the and enables the connected agent (RT-Agent) to send and IEEE 802.15.4 standard. The Atmel set of functions, or- receive data packets. RT-App creates aperiodic tasks for ganized as a network library, have been linked to ERIKA “networking” and “computational” purposes and schedules core. them adopting one of the policies implemented in RTSim, To the best of the authors knowledge, in so far only a few Operat- e.g. First Come First Served (FCFS), Earliest Deadline First ing Systems have been ported to AVR 5 architecture; namely Nano-RK, (EDF), Fixed Priority (FP), etc. TinyOS and recently ERIKA. Conditional compilation is used to customize the cases rupt Service Routine (ISR) initiating the data reception at of ordinary devices and Personal Area Network (PAN) co- the Physical layer of the network stack. The reception com- ordinator. pletes at the MAC layer whenever the payload is extracted The network initialization is organized by means of an from the incoming data frames: depending on the adopted aperiodic task: on the coordinator side, such a task estab- scheduling policy and the computational load present at the lishes a new network, sets the communication mode (peer- sink, the completion may be delayed by some time.
Load more

Recommended publications
  • Efficient Scheduling Library for Freertos
    DEGREE PROJECT IN INFORMATION AND COMMUNICATION TECHNOLOGY, SECOND CYCLE, 30 CREDITS STOCKHOLM, SWEDEN 2016 Efficient Scheduling Library for FreeRTOS ROBIN KASE KTH ROYAL INSTITUTE OF TECHNOLOGY SCHOOL OF INFORMATION AND COMMUNICATION TECHNOLOGY Efficient Scheduling Library for FreeRTOS ROBIN KASE Master’s Thesis at KTH Information and Communication Technology Supervisor: Kenji Kise (Tokyo Institute of Technology) Examiner: Johnny Öberg (KTH) TRITA-ICT-EX-2016:166 Abstract At present, there is a gap between practical implementations of task scheduling on numerous popular Real-Time Operating Systems (RTOSs) and theoretical real-time scheduling. It is difficult to choose what theoretical real-time scheduling concepts to implement when designing a kernel, as theoretical concepts grow and improve over time. Furthermore, the kernel can be kept simpler when offering only simple fixed priority scheduling policy, as advanced scheduling features often require more com- plex implementation and larger overhead. By offering a real-time scheduling library implemented in user space, the user can choose whether to skip the overhead, or use more advanced theories. At the moment there exists already several scheduling frameworks for FreeRTOS. However, they are either difficult to use, not completely implemented in user space, or not providing various theoretical scheduling policies. An open source scheduling library for FreeRTOS implemented in user space that is user friendly and runs with low overhead, Efficient Scheduling Library (ESFree) is proposed. The proposed scheduling library provides polling server that runs aperiodic and sporadic jobs, dependable timing error detection and handling, Rate-Monotonic Scheduling (RMS), Deadline-Monotonic Scheduling (DMS) and Earliest Deadline First (EDF) scheduling policies to provide theoretical real-time scheduling features to speed up development of complex projects, and make FreeRTOS friendlier to students who have newly studied real-time scheduling.
    [Show full text]
  • Download The
    ERIKA Enterprise Current limitations and possible solutions Version: 7 February 11, 2016 DRAFT About Evidence S.r.l. Evidence is a company operating in the field of software for embedded real-time systems. It started in 2002 as a spin-off company of the Real-Time Systems (ReTiS) Lab of the Scuola Superiore Sant'Anna (Pisa, Italy). Today, Evidence is a dynamic company having collaborations in the field of electronics, telecommunications, automotives, and industrial automation. People at Evidence are experts in the domain of embedded and real-time systems, with a deep knowledge on the design and specification flow of embedded software, especially for the embedded market. Besides providing consultancy services, Evidence also provides: BSPs based on Linux for embedded devices, evaluation boards featuring most innovative 8, 16 and 32-bit microcontrollers for the embedded market, development tools for making embedded software development easier, and tools for the schedulability analysis of real-time tasks running on your final product. For more information see: http://www.evidence.eu.com Contact Info Evidence Srl, Via Carducci 56 Localit`aGhezzano 56010 S.Giuliano Terme PISA Italy Tel: +39 050 99 11 224 Fax: +39 050 99 10 812 For more information about Evidence products, please send an e-mail to the follow- ing address: [email protected]. Other information about the Evidence product line can be found at the Evidence web site at: http://www.evidence.eu.com. This document is Copyright 2011-2015 Evidence S.r.l. Information and images contained within this document are copyright and the property of Evidence S.r.l.
    [Show full text]
  • A Fully Open-Source Platform for Automotive Systems
    A fully Open-Source Platform for Automotive Systems Implementation by Paolo Gai, CEO Evidence Srl Bruno Morelli, Evidence Srl 2 The company Founded in 2002, we do custom design and development of software for small embedded devices ~20 qualified people with an average age of 34 years, 30% PhD Experience in automotive, industrial, white goods RTOS and MCU skills • OSEK/VDX, AUTOSAR, • Automatic code generation Embedded Linux skills • 8 Yrs experience in custom BSPs, U-Boot, kernel drivers, • Initial developers of the SCHED_DEADLINE patch 3 Everything in one slide • We created a completely Open-source solution for Automotive systems + • Linux for HMI, communication and logging • ERIKA Enterprise for real-time performance and control • We will show a demo on a dual core Freescale iMX6 • http://erika.tuxfamily.org • Free RTOS for automotive devices • Open-source license , static linking of closed source code • ERIKA Enterprise is the first and only OSEK/VDX certified open-source RTOS 4 Agenda • IVI system requirements and multicore devices • Main features of Erika Enterprise • Success stories • Towards a fully integrated Open-Source solution with Linux and Erika Enterprise • (some) implementation details • Demo on Freescale iMX6 5 Main Requirements of future IVI systems • Fast Boot • there must be a subsystem ready to go in a few ms • Linux boot times are usually in the order of seconds • Real-Time support • there must be a subsystem with real-time performance • e.g. CAN Bus, motor control • Quality of Service • IVI applications need soft-realtime
    [Show full text]
  • ERIKA Enterprise Basic Manual
    ERIKA Enterprise Basic Manual ...multithreading on a thumb! version: 1.1.2 July 18, 2008 About Evidence S.r.l. Evidence is a spin-off company of the ReTiS Lab of the Scuola Superiore S. Anna, Pisa, Italy. We are experts in the domain of embedded and real-time systems with a deep knowledge of the design and specification of embedded SW. We keep providing signifi- cant advances in the state of the art of real-time analysis and multiprocessor scheduling. Our methodologies and tools aim at bringing innovative solutions for next-generation embedded systems architectures and designs, such as multiprocessor-on-a-chip, recon- figurable hardware, dynamic scheduling and much more! Contact Info Address: Evidence Srl, c/o Incubatore Pont-Tech Viale Rinaldo Piaggio, 32 56025 Pontedera (PI), Italy Tel: +39 0587 274 823 Fax: +39 0587 291 904 For more information on Evidence Products, please send an e-mail to the following address: [email protected]. Other informations about the Evidence product line can be found at the Evidence web site at: http://www.evidence.eu.com. This document is Copyright 2005-2008 Evidence S.r.l. Information and images contained within this document are copyright and the property of Evidence S.r.l. All trademarks are hereby acknowledged to be the properties of their respective owners. The information, text and graphics contained in this document are provided for information purposes only by Evidence S.r.l. Evidence S.r.l. does not warrant the accuracy, or completeness of the information, text, and other items contained in this document.
    [Show full text]
  • Embedded Operating Systems
    7 Embedded Operating Systems Claudio Scordino1, Errico Guidieri1, Bruno Morelli1, Andrea Marongiu2,3, Giuseppe Tagliavini3 and Paolo Gai1 1Evidence SRL, Italy 2Swiss Federal Institute of Technology in Zurich (ETHZ), Switzerland 3University of Bologna, Italy In this chapter, we will provide a description of existing open-source operating systems (OSs) which have been analyzed with the objective of providing a porting for the reference architecture described in Chapter 2. Among the various possibilities, the ERIKA Enterprise RTOS (Real-Time Operating System) and Linux with preemption patches have been selected. A description of the porting effort on the reference architecture has also been provided. 7.1 Introduction In the past, OSs for high-performance computing (HPC) were based on custom-tailored solutions to fully exploit all performance opportunities of supercomputers. Nowadays, instead, HPC systems are being moved away from in-house OSs to more generic OS solutions like Linux. Such a trend can be observed in the TOP500 list [1] that includes the 500 most powerful supercomputers in the world, in which Linux dominates the competition. In fact, in around 20 years, Linux has been capable of conquering all the TOP500 list from scratch (for the first time in November 2017). Each manufacturer, however, still implements specific changes to the Linux OS to better exploit specific computer hardware features. This is especially true in the case of computing nodes in which lightweight kernels are used to speed up the computation. 173 174 Embedded Operating Systems Figure 7.1 Number of Linux-based supercomputers in the TOP500 list. Linux is a full-featured OS, originally designed to be used in server or desktop environments.
    [Show full text]
  • Wireless Sensor Network (WSN)
    Catherine Greene Chloe Norris CREU 2010-2011 Wireless Sensor Network (WSN) Detects Uses Temperature Industrial process & Sound monitoring Vibrations Machine monitoring Pressure Monitoring the Motion environment Pollutants Healthcare Home automation Traffic control Source: http://en.wikipedia.org/wiki/Wireless_sensor_network Nodes What it consists of Prices Can have more than one Varies sensor Size Usually has a radio Complexity transceiver A more complex sensor For wireless could be a few hundred communication A less intricate one Small microcontroller could be fairly cheap Energy source Ex: battery Source: http://en.wikipedia.org/wiki/Wireless_sensor_network How they work Sensors support a multi-hop routing algorithm nodes function as forwarders Relay data packets to a base station (known as a wireless ad-hoc network) Think of a sensor like a computer Source: http://en.wikipedia.org/wiki/Wireless_sensor_network Applications Area Monitoring WSN would be put in an area where something is being monitored Ex: a country at war with another may place nodes over a battlefield to detect enemy intrusion, sensors would detect heat, pressure, sound, light, electro-magnetic fields, vibrations, etc… If a sensor went off it would report it to a base station (message might be sent through internet or satellite) Ex: detecting vehicles Source: http://en.wikipedia.org/wiki/Wireless_sensor_network Applications Environmental Monitoring Similar to area monitoring Ex (pictured): state of permafrost in the Swiss Alps
    [Show full text]
  • Paralel Gerçek Zamanli Kiyaslama Uygulama Takimi
    T.C. SAKARYA ÜNİVERSİTESİ FEN BİLİMLERİ ENSTİTÜSÜ PARALEL GERÇEK ZAMANLI KIYASLAMA UYGULAMA TAKIMI YÜKSEK LİSANS TEZİ Sevil SERTTAŞ Enstitü Anabilim Dalı : BİLGİSAYAR VE BİLİŞİM MÜHENDİSLİĞİ Tez Danışmanı : Dr. Öğr. Üyesi Veysel Harun ŞAHİN Nisan 2019 TEŞEKKÜR Yüksek lisans eğitimim boyunca değerli bilgi ve deneyimlerinden yararlandığım, araştırmanın planlanmasından yazılmasına kadar tüm aşamalarında yardımlarını esirgemeyen değerli danışman hocam Dr. Öğr. Üyesi Veysel Harun ŞAHİN’e teşekkürlerimi sunarım. i İÇİNDEKİLER TEŞEKKÜR ........................................................................................................... i İÇİNDEKİLER ...................................................................................................... ii SİMGELER VE KISALTMALAR LİSTESİ ....................................................... iv ŞEKİLLER LİSTESİ ............................................................................................. v TABLOLAR LİSTESİ ........................................................................................... vi ÖZET ..................................................................................................................... vii SUMMARY ........................................................................................................... viii BÖLÜM 1. GİRİŞ …………………………………………………………….................................... 1 BÖLÜM 2. WCET .................................................................................................................... 3 BÖLÜM 3. KIYASLAMA UYGULAMALARI
    [Show full text]
  • COMPARATIVE ANALYSIS of DIFFERENT OPERATING SYSTEMS USED for LOW-END IOT DEVICES 1ZURABIA RIAZ 1University of Management and Technology, Lahore, Pakistan
    VFAST Transactions on Software Engineering http://vfast.org/journals/index.php/VTSE@ 2020 ISSN(e): 2309-3978;ISSN(p): 2411-6246 Volume 8, Number 1, January-December, 2020 pp. 64-72 COMPARATIVE ANALYSIS OF DIFFERENT OPERATING SYSTEMS USED FOR LOW-END IOT DEVICES 1ZURABIA RIAZ 1University of Management and Technology, Lahore, Pakistan. [email protected] Abstract-Internet of Things is the new emerging field projected to interconnect billions of devise through the internet. IoT devices divided into high end as well as low end devices. Linux based operating systems can easily handle IoT based high end devices and due to resource based constraints that includes very less memory, energy power for computation of low end IoT devices makes it difficult to develop. In this paper the main focus is on the detail discussions of the operating systems that will satisfy the requirements of IoT devices for low end categories. Comparative analysis will be performed for different operating system and then the by keeping the focus on the OS which are close to Linux and are fit for the low end IoT devices. Keywords: Internet of Things, Low End Devices, embedded systems 1. Introduction:. Internet of Things or IoT can be root as the availability of excessive and multiple devices (things) interconnected with embedded devices to send and receive data via Internet.For communication different standards for communicating protocols at network layer in-combination with IPv6 has been developed. These protocols as a result enable the heterogeneous devices to connect through internet. In context with hardware, IoT is a collected combination of hardware devices which are heterogeneous in nature.
    [Show full text]
  • Tcc Engenharia Eletrica
    UNIVERSIDADE DO SUL DE SANTA CATARINA MAX BACK SISTEMA EMBARCADO COM RTOS: UMA ABORDAGEM PRÁTICA E VOLTADA A PORTABILIDADE Palhoça 2018 MAX BACK SISTEMA EMBARCADO COM RTOS: UMA ABORDAGEM PRÁTICA E VOLTADA A PORTABILIDADE Trabalho de Conclusão de Curso apresentado ao Curso de Graduação em Engenharia Elétrica com ênfase em Telemática da Universidade do Sul de Santa Catarina como requisito parcial à obtenção do título de Engenheiro Eletricista. Orientador: Prof. Djan de Almeida do Rosário, Esp. Eng. Palhoça 2018 Dedico este trabalho а Deus, por ser o verdadeiro princípio e fim de todas as coisas (das que valem a pena). AGRADECIMENTOS Agradeço a minha esposa Gizele e meus filhos, Eric e Thomas, meus pais e a toda minha família que, com muito carinho е apoio, não mediram esforços para que eu chegasse até esta etapa de minha vida. Agradeço aos professores do curso por terem transmitido seu conhecimento a mim e meus colegas com tanto empenho e dedicação. Não existe triunfo sem perda, não há vitória sem sofrimento, não há liberdade sem sacrifício. (O Senhor dos Anéis – J.R.R. Tolkien, 1954) RESUMO A crescente demanda pelo desenvolvimento de solução conectadas entre sistemas já existentes, assim como a ampliação do uso destes sistemas embarcados mostram a importância de soluções robustas, de tempo real, com ciclos de desenvolvimento cada vez mais curtos e necessidade de reaproveitamento de código. Este trabalho apresenta a seleção do sistema operacional de tempo real FreeRTOS e o experimento de sua utilização como base para o desenvolvimento de um controlador wearable (vestível) em duas plataformas de hardware diferentes, implementando a solução inicialmente em uma delas e depois portando para a outra plataforma, desenvolvendo principalmente a programação específica do novo hardware e procurando manter a parte da aplicação inalterada e independente de plataforma.
    [Show full text]
  • Designing High Throughput Routing Protocol for Wireless Body Area Networks
    International Journal of Technical Research and Applications e-ISSN: 2320-8163, www.ijtra.com Volume 6, Issue 2 (MARCH-APRIL 2018), PP. 85-91 DESIGNING HIGH THROUGHPUT ROUTING PROTOCOL FOR WIRELESS BODY AREA NETWORKS Noor khateeb Ali Khan 1, Shashank Singh 2, Department Of Computer Science Engineering Integral University Lucknow, India Abstract—Wireless Body Area Network (WBAN) is new emerging sub-field of WSN. A key application of Wireless Body A. BAN Positioning Area Network is health monitoring. Wireless sensors are placed BAN is described as a short-range, low-powered device on the human body or implanted in the body to monitor vital that operates around the human body (not limited to humans) signs like blood pressure, body temperature, heart rate, glucose providing a variety of applications. These applications may level etc. Use of Wireless Body Area Network technology to include medical, personal entertainment and consumer monitor health parameters significantly reduces the expenditures electronics. BANs can be described as special WSNs that have of patient in hospital. Wireless Body Area Sensors are used to monitor human health with limited energy resources. Different lesser nodes and much reliable with special importance placed energy efficient routing schemes are used to forward data from on QoS as compared to the tradition WSN. BAN in some cases body sensors to medical server. It is important that sensed data is referred to as BSN. of patient reliably received to medical specialist for further The positioning of BAN in relation with other wireless analysis. To minimize energy consumption and to increase the networks is shown in figure 1.
    [Show full text]
  • ERIKA Enterprise Minimal API Manual
    ERIKA Enterprise Minimal API Manual ...multithreading on a thumb! version: 1.1.3 December 11, 2012 About Evidence S.r.l. Evidence is a spin-off company of the ReTiS Lab of the Scuola Superiore S. Anna, Pisa, Italy. We are experts in the domain of embedded and real-time systems with a deep knowledge of the design and specification of embedded SW. We keep providing signifi- cant advances in the state of the art of real-time analysis and multiprocessor scheduling. Our methodologies and tools aim at bringing innovative solutions for next-generation embedded systems architectures and designs, such as multiprocessor-on-a-chip, recon- figurable hardware, dynamic scheduling and much more! Contact Info Address: Evidence Srl, Via Carducci 56 Localit`aGhezzano 56010 S.Giuliano Terme Pisa - Italy Tel: +39 050 991 1122, +39 050 991 1224 Fax: +39 050 991 0812, +39 050 991 0855 For more information on Evidence Products, please send an e-mail to the following address: [email protected]. Other informations about the Evidence product line can be found at the Evidence web site at: http://www.evidence.eu.com. This document is Copyright 2005-2012 Evidence S.r.l. Information and images contained within this document are copyright and the property of Evidence S.r.l. All trademarks are hereby acknowledged to be the properties of their respective owners. The information, text and graphics contained in this document are provided for information purposes only by Evidence S.r.l. Evidence S.r.l. does not warrant the accuracy, or completeness of the information, text, and other items contained in this document.
    [Show full text]
  • Levels of Specialization in Real-Time Operating Systems
    Levels of Specialization in Real-Time Operating Systems Björn Fiedler, Gerion Entrup, Christian Dietrich, Daniel Lohmann Leibniz Universität Hannover {fiedler, entrup, dietrich, lohmann}@sra.uni-hannover.de Abstract—System software, such as the RTOS, provides no robustness, security and so on; it increases the safety margins or business value on its own. Its utility and sole purpose is to serve makes it possible to cut per-unit-costs by switching to a cheaper an application by fulfilling the software’s functional and nonfunc- hardware. For price-sensitive domains of mass production, such tional requirements as efficiently as possible on the employed as automotive, this is of high importance [8]. hardware. As a consequence, every RTOS today provides some means of (static) specialization and tailoring, which also has a Intuitively, any kind of specialization requires knowledge long tradition in the general field of system software. about the actual application: The more we know, the better However, the achievable depth of specialization, the resulting we can specialize. In the domain of real-time systems (RTSs), benefits, but also the complexity to reach them differ a lot we typically know a lot about our application and its exe- among systems. In the paper, we provide and discuss a taxonomy cution semantics on the employed RTOS: To achieve real- for (increasing) levels of specialization as offered by (real-time) time properties, all resources need to be bounded and are system software today and in the future. We argue that system software should be specialized as far as possible – which is scheduled deterministically. Timing analysis depends on the always more than you think – but also discuss the obstacles that exact specification of inputs and outputs, including their inter- hinder specialization in practice.
    [Show full text]