A real-time system is a system such that the correctness of operations depends not only on the logical results, but also on the time at which these results are available. A fundamental problem in designing real-time systems is to analyze response time of operations, which is defined as the time elapsed from the moment when the operation is requested to the moment when the operation is completed. Response time analysis is challenging due to the complex dynamics among operations. A common technique is to study response time under worst-case scenario. However, using worst-case response time may lead to the conservative real-time system designs. To improve the real-time system design, we analyze the non-worst-case response time of operations and apply these results in the design process. The main contribution of this thesis includes mathematical modeling of real-time systems, calculation of non-worst-case response time, and improved real-time system design. We perform analysis and design on three common types of real-time systems as the real-time computing system, real-time communication network, and real-time energy management. For the real-time computing systems, our non-worst-response time analysis leads a necessary and sufficient online schedulability test and a measure of robustness of real-time systems. For the real-time communication network, our non-worst-response time analysis improves the performance for the model predictive control design based on the real-time communication network. For the real-time energy management, we use the non-worst-case response time to check whether the micro-grid can operate independently from the main grid.

Thesis (M. Sc.)--Carleton University, 2004. / Includes bibliographical references (p. 95-99). Also available in electronic format on the Internet.

The increasing dependency of man on machines have led to increase computational load on systems. The increasing computational load can be handled to some extent by scaling up processor frequencies. However, this approach has hit a frequency and power wall and the increasing awareness towards green computing discourages this solution. This leads us to use multi-core architectures. Due to the same reason, real-time systems are also migrating from single-core towards multi-core systems. While multi-core systems provide scalable high computational power, they also expose real-time systems to several challenges. Most of these challenges hamper the key property of real-time systems, i.e., predictability. In this work, we address some challenges imposed by multi-core architectures on real-time systems. We propose and evaluate several scheduling algorithms and demonstrate improved predictability and performance over existing methods. A unifying them in all our algorithms is that we explicitly consider the effects of architectural factors on the scheduling and schedulablity of real-time programs. As a case study, we use Tilera's TilePro64 platform as an example multi-core platform and implement some of our algorithms on this platform. Through this case study, we derive several useful conclusions regarding performance, predictability and practical overheads on a multi-core architecture.

Hybrid error control techniques to improve data communication performance for noisy channels have been extensively studied. However, a growing concern in communication system design is the impact of delay due to retransmissions and/or delay-prone technologies on system performance. Previous analyses have not considered various delay aspects of a hybrid error control system. Efficient error control techniques which are able to provide improved coding gain and throughput by promptly matching the error correction coding capability with the changing channel conditions have yet to be developed and investigated. In this thesis, delay-related performance characteristics are investigated for asynchronous time division multiplexing links. Two different methods based on an imbedded Markov chain model are developed and applied to the system with a noisy feedback channel, yielding analytical expressions for the buffer occupancy and the block delay. A recursive expression for packet loss probability for systems with a finite transmitter buffer is obtained. The concept of delay-limited error control coding is introduced for real-time communications. Performance improvement by truncation of a type-II hybrid-ARQ protocol with one retransmission is investigated in detail. It is shown that the truncated protocol has a bounded delay and bounded queue length under typical communication traffic conditions. The error performance of the truncated protocol is further analyzed for various mobile fading channels. Matched-rate hybrid error control coding for both adaptive and non-adaptive cases is also studied. A new adaptive error control protocol using Reed-Solomon codes is proposed. The protocol uses novel feedback transmissions to achieve faster estimation of channel states. Numerical optimization is carried out by introducing overall throughput and modified throughput as efficiency criteria. Based on channel bit error rate measurement, optimum overall throughput is obtained with minimum implementation complexity. Our general conclusions are: (1) Both delay and packet loss can be greatly reduced by incorporating a Reed-Solomon code into the data-link protocol for noisy channels. (2) The truncated hybrid error control protocol can provide coding gain improvement and reduced delay over the conventional (untruncated) protocol. (3) Throughput efficiency of a type-I or type-II hybrid-ARQ protocol can be significantly improved by using the proposed matched-rate error control techniques. / Graduate

This thesis is related to the knowledge area of real-time systems and real-time databases. The increasing complexity of the systems, specifically the embedded systems, and the need of store and share the information they use leads to the need of new technologies. For this reason a need of real-time database management system has emerged to satisfy the new requirements. Several commercial database systems claim to be real-time, but this technology is not consolidated enough. The thesis will perform an evaluation of those databases mainly in predictability terms since predictability is necessary for the correct execution of hard real-time systems. In order to complete the evaluation, a real-time database application has been implemented. This application implements two commercial databases, namely Mimer and eXtremeDB, and a monitor application which is responsible for displaying all the relevant database behavior’s information at runtime. A comparative studying of both databases has been carried out in order to determine how predictable these databases are. Parameters such as response time, CPU time consumption, etc has been studied. Finally, it can be concluded that both databases are predictable to a certain level. On one hand Mimer has an estimation of the worst case response time around 12 µs and CPU overload of 36%, and the fluctuation along the transactions is nearly negligible. On the other hand, eXtreme has an estimation of the worst-case response time around 18 µs and CPU overload of 41%, and the fluctuation along the transactions are rather bigger than the Mimer’s. However, it can be concluded that both databases provide real-time transactions and, thus, they are able to be implemented in real-time systems.

Development of distributed real-time applications, in contrast to best effort applications, traditionally have been a slow process due to the lack of available standards, and the fact that no commercial off the shelf (COTS) distributed object computing (DOC) middleware supporting real-time requirements have been available to use, in order to speed up the development process without sacrificing any quality. Standards and DOC middlewares are now emerging that are addressing key requirements of real-time systems, predictability and efficiency, and therefore, new possibilities such as component decomposition of real-time systems arises. A number of component decomposed architectures of the distributed active real-time database system DeeDS is described and discussed, along with a discussion on the most suitable DOC middleware. DeeDS is suitable for this project since it supports hard real-time requirements and is distributed. The DOC middlewares that are addressed in this project are OMG's Real-Time CORBA, Sun's Enterprise JavaBeans, and Microsoft's COM/DCOM. The discussion to determine the most suitable DOC middleware focuses on real-time requirements, platform support, and whether implementations of these middlewares are available.

The first conference on Real-Time Mining is bringing together individuals and companies working on EU-sponsored projects to exchange knowledge and rise synergies in resource extraction innovation. The topics include: • Resource Modelling and Value of Information; • Automated Material Characterization; • Positioning and Material Tracking; • Process Optimization; • Data Management. The conference has been initiated by the consortium of the EU H2020 funded project Real-Time Mining as a platform for inter-project communication and for communication with project stakeholders. It brings together several European research projects in the field of industry 4.0 applied to mineral resource extraction. These are the projects VAMOS, SOLSA and UNEXMIN.

The flow of information, and consequently the decision-making along the chain of mining from exploration to beneficiation, typically occurs in a discontinuous fashion over long timespans. In addition, due to the uncertain nature of the knowledge about deposits and the inherent spatial distribution of material characteristics, actual production performance often deviates from expectations. Reconciliation exercises to adjust mineral resource and reserve models and planning assumptions are performed with timely lags of weeks, months or even years.

Combined mineralogical and chemical analyses on drill cores are highly demanded by mining and metallurgical companies to speed up exploration, mining and define geometallurgical parameters for beneficiation. Furthermore, high quality coherent and complete drill cores are needed to obtain reliable analyses for more accurate geomodels, resource and reserve estimates. At present, analyses are done by exploiting only a single technique, such as hyperspectral imaging, XRF or LIBS. The coupling of different analytical instruments is still a technological challenge. The SOLSA project, sponsored by the EU-H2020 Raw Material program, targets to construct an expert system coupling sonic drilling with XRF, XRD, hyperspectral imaging and Raman spectroscopy. This paper will present the 4-years project in progress, a general, almost mid-term, state-of-the-art.

The 42-month ¡VAMOS! project (Viable Alternative Mine Operating System, Grant Agreement 642477, vamos-project.eu), co-funded by the European Commission’s Horizon2020 programme, will enable access to reserves of mineral deposits by developing an innovative, safe, clean, and low-visibility underwater inland mining technique. Through field-testing, ¡VAMOS! hopes to encourage investment in abandoned and prospective EU open-pit mines by providing a viable novel excavation process, ultimately aiming to reduce the EU’s reliance on imports of strategically important raw materials. The project will test the technological and economic viability of the underwater mining of inland mineral deposits which are currently economically, technologically, and environmentally unobtainable. If proven viable, ¡VAMOS! will enable access to deposits whose excavation has been historically limited by stripping ratio and hydrological and geotechnical considerations. Also, due to low noise and dust levels, and its road-transportable electric-powered system, ¡VAMOS! will be able to be applied safely in both urban-proximal and hard-to-access rural locations. ¡VAMOS! is defined by a remotely-operated underwater mining vehicle, adapted and improved from existing subsea mining technology. Operating in tandem with a remote-controlled sensory assistance-vehicle, the underwater miner will connect to a flexible riser through which mined material will be pumped from the mudline to a land-based dewatering pit via a floating mobile deployment-platform. On the deployment platform, a bypass system will be linked to production measuring equipment and a laser-induced breakdown spectroscopy system, enabling throughput monitoring and real-time grade-control. Preparatory work has been carried out to assess the regulatory compliance of the project, its likely social and environmental impact, and the steps which need to be taken to reduce and quantify these during testing. Two community stakeholder workshops held in both England and Portugal have indicated that the public is receptive to the concept. Following an official project design-freeze in October 2016, construction and integration of all components will conclude in June 2017. This will be followed by field-testing at a flooded kaolin-granite quarry in Devon, England in October 2017, with further testing planned at a flooded iron mine in Vareš, Bosnia in June 2018.