Replication management in reliable real-time systems

Building reliable real-time applications on top of commercial off-the-shelf (COTS) components is not a straightforward task. Thus, it is essential to provide a simple and transparent programming model, in order to abstract programmers from the low-level implementation details of distribution and replication. However, the recent trend for incorporating pre-emptive multitasking applications in reliable real-time systems inherently increases its complexity. It is therefore important to provide a transparent programming model, enabling pre-emptive multitasking applications to be implemented without resorting to simultaneously dealing with both system requirements and distribution and replication issues. The distributed embedded architecture using COTS components (DEAR-COTS) architecture has been previously proposed as an architecture to support real-time and reliable distributed computer-controlled systems (DCCS) using COTS components. Within the DEAR-COTS architecture, the hard real-time subsystem provides a framework for the development of reliable real-time applications, which are the core of DCCS applications. This paper presents the proposed framework, and demonstrates how it can be used to support the transparent replication of software components.

Cycle time properties of the PROFIBUS timed-token protocol

A recent trend in distributed computer-controlled systems (DCCS) is to interconnect the distributed computing elements by means of multi-point broadcast networks. Since the network medium is shared between a number of network nodes, access contention exists and must be solved by a medium access control (MAC) protocol. Usually, DCCS impose real-time constraints. In essence, by real-time constraints we mean that traffic must be sent and received within a bounded interval, otherwise a timing fault is said to occur. This motivates the use of communication networks with a MAC protocol that guarantees bounded access and response times to message requests. PROFIBUS is a communication network in which the MAC protocol is based on a simplified version of the timed-token protocol. In this paper we address the cycle time properties of the PROFIBUS MAC protocol, since the knowledge of these properties is of paramount importance for guaranteeing the real-time behaviour of a distributed computer-controlled system which is supported by this type of network.

Supporting real-time distributed computer-controlled systems with multi-hop P-NET networks

Fieldbus communication networks aim to interconnect sensors, actuators and controllers within process control applications. Therefore, they constitute the foundation upon which real-time distributed computer-controlled systems can be implemented. P-NET is a fieldbus communication standard, which uses a virtual token-passing medium-access-control mechanism. In this paper pre-run-time schedulability conditions for supporting real-time traffic with P-NET networks are established. Essentially, formulae to evaluate the upper bound of the end-to-end communication delay in P-NET messages are provided. Using this upper bound, a feasibility test is then provided to check the timing requirements for accessing remote process variables. This paper also shows how P-NET network segmentation can significantly reduce the end-to-end communication delays for messages with stringent timing requirements.

Communication response time in P-NET networks: worst-case analysis considering the actual token utilisation

Fieldbus networks aim at the interconnection of field devices such as sensors, actuators and small controllers. Therefore, they are an effective technology upon which Distributed Computer Controlled Systems (DCCS) can be built. DCCS impose strict timeliness requirements to the communication network. In essence, by timeliness requirements we mean that traffic must be sent and received within a bounded interval, otherwise a timing fault is said to occur. P-NET is a multi-master fieldbus standard based on a virtual token passing scheme. In P-NET each master is allowed to transmit only one message per token visit, which means that in the worst-case the communication response time could be derived considering that the token is fully utilised by all stations. However, such analysis can be proved to be quite pessimistic. In this paper we propose a more sophisticated P-NET timing analysis model, which considers the actual token utilisation by different masters. The major contribution of this model is to provide a less pessimistic, and thus more accurate, analysis for the evaluation of the worst-case communication response time in P-NET fieldbus networks.

Timing analysis of an inter-cell mobility procedure for a wired/wireless PROFIBUS network

Recently, there have been a few research efforts towards extending the capabilities of fieldbus networks to encompass wireless support. In previous works we have proposed a hybrid wired/wireless PROFIBUS network solution where the interconnection between the heterogeneous communication media was accomplished through bridge-like interconnecting devices. The resulting networking architecture embraced a Multiple Logical Ring (MLR) approach, thus with multiple independent tokens, where the communication between different domains was supported by the Inter-Domain Protocol (IDP). The proposed architecture also supports mobility of stations between different wireless cells. To that hybrid wired/wireless networking architecture we have proposed a worst-case response timing analysis of the IDP, without considering inter-cell mobility (or handoff) of stations. In this paper, we advance that previous work by proposing a worst-case timing analysis of the mobility procedure.

Timeliness in COTS factory-floor distributed systems: What role for simulation?

In the past few years, a significant amount of work has been devoted to the timing analysis of Ethernet-based technologies. However, none of these address the problem of timeliness evaluation at a holistic level. This paper describes a research framework embracing this objective. It is advocated that, simulation models can be a powerful tool, not only for timeliness evaluation, but also to enable the introduction of less pessimistic assumptions in an analytical response time approach, which, most often, are afflicted with simplifications leading to pessimistic assumptions and, therefore, delusive results. To this end, we address a few inter-linked research topics with the purpose of setting a framework for developing tools suitable to extract temporal properties of commercial-off-the-shelf (COTS) factory-floor communication systems.

Enabling inter-domain transactions in bridge-based hybrid wired/wireless PROFIBUS networks

The marriage of emerging information technologies with control technologies is a major driving force that, in the context of the factory-floor, is creating an enormous eagerness for extending the capabilities of currently available fieldbus networks to cover functionalities not considered up to a recent past. Providing wireless capabilities to such type of communication networks is a big share of that effort. The RFieldbus European project is just one example, where PROFIBUS was provided with suitable extensions for implementing hybrid wired/wireless communication systems. In RFieldbus, interoperability between wired and wireless components is achieved by the use specific intermediate networking systems operating as repeaters, thus creating a single logical ring (SLR) network. The main advantage of the SLR approach is that the effort for protocol extensions is not significant. However, a multiple logical ring (MLR) approach provides traffic and error isolation between different network segments. This concept was introduced in, where an approach for a bridge-based architecture was briefly outlined. This paper will focus on the details of the inter-Domain Protocol (IDP), which is responsible for handling transactions between different network domains (wired or wireless) running the PROFIBUS protocol.

Reliable real-time communication in CAN networks

Controller area network (CAN) is a fieldbus network suitable for small-scale distributed computer controlled systems (DCCS), being appropriate for sending and receiving short real-time messages at speeds up to 1 Mbit/sec. Several studies are available on how to guarantee the real-time requirements of CAN messages, providing preruntime schedulability conditions to guarantee the real-time communication requirements of DCCS traffic. Usually, it is considered that CAN guarantees atomic multicast properties by means of its extensive error detection/signaling mechanisms. However, there are some error situations where messages can be delivered in duplicate or delivered only by a subset of the receivers, leading to inconsistencies in the supported applications. In order to prevent such inconsistencies, a middleware for reliable communication in CAN is proposed, taking advantage of CAN synchronous properties to minimize the runtime overhead. Such middleware comprises a set of atomic multicast and consolidation protocols, upon which the reliable communication properties are guaranteed. The related timing analysis demonstrates that, in spite of the extra stack of protocols, the real-time properties of CAN are preserved since the predictability of message transfer is guaranteed.

Assigning real-time tasks on heterogeneous multiprocessors with two unrelated types of processors

A preliminary version of this paper appeared in Proceedings of the 31st IEEE Real-Time Systems Symposium, 2010, pp. 239–248.

Convex optimization framework for intermediate deadline assignment in soft and hard real-time distributed systems

It is generally challenging to determine end-to-end delays of applications for maximizing the aggregate system utility subject to timing constraints. Many practical approaches suggest the use of intermediate deadline of tasks in order to control and upper-bound their end-to-end delays. This paper proposes a unified framework for different time-sensitive, global optimization problems, and solves them in a distributed manner using Lagrangian duality. The framework uses global viewpoints to assign intermediate deadlines, taking resource contention among tasks into consideration. For soft real-time tasks, the proposed framework effectively addresses the deadline assignment problem while maximizing the aggregate quality of service. For hard real-time tasks, we show that existing heuristic solutions to the deadline assignment problem can be incorporated into the proposed framework, enriching their mathematical interpretation.

Distributed computing for the factory-floor: a real-time approach using WorldFIP networks

Field communication systems (fieldbuses) are widely used as the communication support for distributed computer-controlled systems (DCCS) within all sort of process control and manufacturing applications. There are several advantages in the use of fieldbuses as a replacement for the traditional point-to-point links between sensors/actuators and computer-based control systems, within which the most relevant is the decentralisation and distribution of the processing power over the field. A widely used fieldbus is the WorldFIP, which is normalised as European standard EN 50170. Using WorldFIP to support DCCS, an important issue is “how to guarantee the timing requirements of the real-time traffic?” WorldFIP has very interesting mechanisms to schedule data transfers, since it explicitly distinguishes periodic and aperiodic traffic. In this paper, we describe how WorldFIP handles these two types of traffic, and more importantly, we provide a comprehensive analysis on how to guarantee the timing requirements of the real-time traffic.

Fieldbus networks: real-time from the perspective of the application tasks

Fieldbus communication networks aim to interconnect sensors, actuators and controllers within distributed computer-controlled systems. Therefore they constitute the foundation upon which real-time applications are to be implemented. A potential leap towards the use of fieldbus in such time-critical applications lies in the evaluation of its temporal behaviour. In the past few years several research works have been performed on a number of fieldbuses. However, these have mostly focused on the message passing mechanisms, without taking into account the communicating application tasks running in those distributed systems. The main contribution of this paper is to provide an approach for engineering real-time fieldbus systems where the schedulability analysis of the distributed system integrates both the characteristics of the application tasks and the characteristics of the message transactions performed by these tasks. In particular, we address the case of system where the Process-Pascal multitasking language is used to develop P-NET based distributed applications

Integrating inaccessibility in response time analysis of CAN networks

Controller Area Network (CAN) is a fieldbus network suitable for small-scale Distributed Computer Controlled Systems, being appropriate for transferring short real-time messages. Nevertheless, it must be understood that the continuity of service is not fully guaranteed, since it may be disturbed by temporary periods of network inaccessibility [1]. In this paper, such temporary periods of network inaccessibility are integrated in the response time analysis of CAN networks. The achieved results emphasise that, in the presence of temporary periods of network inaccessibility, a CAN network is not able to provide different integrity levels to the supported applications, since errors in low priority messages interfere with the response time of higher priority message streams.

Using WorldFIP networks to support periodic and sporadic real-time traffic

In this paper we address the ability of WorldFIP to cope with the real-time requirements of distributed computer-controlled systems (DCCS). Typical DCCS include process variables that must be transferred between network devices both in a periodic and sporadic (aperiodic) basis. The WorldFIP protocol is designed to support both types of traffic. WorldFIP can easily guarantee the timing requirements for the periodic traffic. However, for the aperiodic traffic more complex analysis must be made in order to guarantee its timing requirements. This paper describes work that is being carried out to extend previous relevant work, in order to include the actual schedule for the periodic traffic in the worst-case response time analysis of sporadic traffic in WorldFIP networks

Replica management in real-time Ada 95 applications

In this paper, we present some of the fault tolerance management mechanisms being implemented in the Multi-μ architecture, namely its support for replica non-determinism. In this architecture, fault tolerance is achieved by node active replication, with software based replica management and fault tolerance transparent algorithms. A software layer implemented between the application and the real-time kernel, the Fault Tolerance Manager (FTManager), is the responsible for the transparent incorporation of the fault tolerance mechanisms The active replication model can be implemented either imposing replica determinism or keeping replica consistency at critical points, by means of interactive agreement mechanisms. One of the Multi-μ architecture goals is to identify such critical points, relieving the underlying system from performing the interactive agreement in every Ada dispatching point.