Wireless Mesh Networks (WMNs) provide a promising foundation for a flexible and reliable communication infrastructure in industrial environments. Meeting the QoS demands of industrial applications, though, requires the deployment of an admission control to avoid network overload. The presence of mobile stations, however, causes dynamics within the network that severely impacts the available capacity. For instance, if a communication route switches from one to two hops, twice the resources are consumed due to self-interference. To neither jeopardize QoS guarantees nor having to cancel present flows, our dependable admission control scheme foresees and considers those dynamics during resource reservation to handle station mobility. We describe a highly dependable approach and further propose an estimation method that improves network efficiency. The evaluation results show that our novel approach allows for a dependable admission control even in presence of mobile stations and thus enables the network to provide a new class of guarantee for mission-critical mobile applications.

The deployment of wireless communication networks in industrial facilities allows for increased flexibility and seamless integration of mobile participants. Time-critical control applications are generally realized with dedicated wireless sensor networks while common WLAN infrastructure networks allow high-throughput best-effort communication. To provide high-capacity communication as well as real-time service quality, we developed and implemented a Wireless Mesh Network (WMN) infrastructure for industrial applications. An example application that requires these properties is the video-based tele-operation of a mobile robot, which we present as case study in this work. It shows the applicability of our infrastructure as well as the necessity of its comprised components.

Deploying wireless technologies in industrial automation becomes more and more common. It is an enabler for many innovative applications where moving system components are involved, e. g. rotating parts of machines. However, many of such applications impose high temporal requirements on the wireless system, for instance isochronous data communication. Today, these requirements can not be met by existing solutions, such as IEEE802.11 Wireless Local Area Networks (WLANs). In this paper, an isochronous wireless communication system is investigated. It mainly consists of a deterministic medium access control, based on IEEE 802.11, which is extended with additional features for isochronous communication. The presented preliminary analysis shows the system's feasibility for the targeted industrial applications and presents promising performance improvements in comparison with standard mechanisms.

Wireless mesh networks offer flexibility for industrial automation, but, in these environments with changing propagation conditions, it is challenging to guarantee the radio coverage and connectivity. This paper contributes a new localization-based method for the calibration of radio propagation models. The idea is to find the locations of the mobile stations via localization and to use radio signal strength measurements from them for adjusting the radio model parameters until the model better fits to the real environment. This calibration method is integrated in our previously published fault-tolerance framework for guaranteeing the availability of radio coverage and connectivity of wireless mesh networks. It is used to automatically detect environmental dynamics (errors) at run-time and to propose a network reconfiguration before they lead to service failures. An evaluation in a real industrial scenario shows the practicability of our approach.

Wireless Mesh Networks (WMNs) are a promising technology for industrial environment communication because of their high flexibility and low cost. To fulfill the thereby arising reliability demands, admission control can be used to prevent congestion and to provide end-to-end guarantees to applications. However, this requires a very precise modeling of the medium utilization for existing and requested data flows, which is challenging due to the dynamics of such networks. In this paper we propose a medium utilization model for small-scale multi-rate WMNs considering the end-to-end throughput. The model is integrated into a feedback control loop to allow an admission control mechanism to ensure reliable end-to-end communication. Our approach increases the available performance without sacrificing reliability. A real test-bed evaluation shows that our admission control manager allows to fully utilize the network capacity while keeping packet losses under 0.5% and three-hop latency below 5.5ms. This is a significant improvement towards reliable multi-rate WMNs, leveraging their applicability in industrial applications with high throughput demands.

Wireless Mesh Networks are infrastructure networks with a wireless multi-hop backbone. In this paper we present an innovative algorithm for fault-tolerant base station planning in wireless mesh networks. The algorithm determines a close-to-minimal number and the positions of base stations to be installed such that the radio coverage is correct in the presence of faults (base station crash or link outage). The algorithm considers both the connectivity of the multi-hop backbone and the connectivity of the mobile stations. The presented algorithm produces correct results, in limited number of iterations under realistic network size and in acceptable time. The provided fault-tolerance is sufficient in most practical situations.

Wireless Mesh Networks (WMN) provide a flexible and inexpensive way to expand network applications to mobile entities. However, high communication reliability demands can not be met by regular WMNs due to mobility and inherent properties of wireless communication. Failing links are common events which impose a major challenge for providing a dependable communication service. By the use of suitable cross-layer models, we provide a timely detection of failed links without compromising the network stability. It is shown that the packet loss caused by a link failure can be reduced from a time-dependent value to at most four consecutive packets. For a typical control application this means an improvement by a factor of 100. In addition to an empirical evaluation we demonstrate the applicability of the mechanism by utilizing it in a real-world WMN to allow the tele-operation of a mobile robot.

Mobile robot applications operating in wireless environments require fast detection of link failures in order to enable fast repair. In previous work, we have shown that cross-layer failure detection can reduce failure detection latency significantly. In particular, we monitor the behavior of the WLAN MAC layer to predict failures on the link layer. In this paper, we investigate data mining techniques to determine which parameters, i.e., the events, or combination and timing of events, occurring on the MAC layer most probably lead to link failures. Our results show, that the parameters revealed with the data mining approach produce similar or even more accurate failure predictions than achieved so far.

This paper addresses questions of using wireless mesh networks (WMNs) in heterogeneous industrial infrastructures. This implies several problems like global addressing, handling of QoS requirements, interconnection with embedded networks. Our proposed solution is a publish/subscribe middleware. We discuss how it solves the mentioned problems. Real-world measurements and simulation results give an idea of QoS properties. A case study of controlling a mobile robot is presented. The results show that the middleware is well suited for non-critical control and monitoring tasks.

Wireless Mesh Networks (WMNs) are gaining popularity in many application areas because of their low cost and high flexibility. Technically, a WMN forms a distributed network-centric system which aims to provide communication services to the application layer, but has no built-in dependability provisions. To make the network dependable, many problems have to be solved on different layers. With this paper, we describe our ongoing work to provide an integrated solution to increase the dependability of WMNs. Our approach combines network coverage planning on the physical layer, bandwidth management on the link layer and live network monitoring to improve the reliability, availability and maintainability of a WMN. We provide fine-grained means to improve the predictability of the network components, thus making the WMN more dependable. In this paper, we present first results of our work, and describe how they are interleaved.

Wireless mesh networks are a promising backbone-solution for applications in industrial automation. However, high availability of the communication channel is not inherently guaranteed because of environment-dynamics and unauthorized users congesting the medium. In this paper we propose a method to increase channel-availability. We use an automated coverage planning method with feedback from the environment to cope with environment-dynamics. Unauthorized users can be automatically localized: this eases their finding and elimination. Our experimental evaluation shows that the method estimates the actual network coverage with an accuracy of 10 dB; users are located with 3.7 m accuracy on average. The main improvement of the coverage planning and localization methods is the achieved autonomy in dynamic environments. Therefore channel-availability also increases.

Typically wireless networks coverage is planned with static redundancy to compensate temporal variations in the environment. As a result, the service still is delivered but the network coverage could have entered a critical state, meaning that further changes in the environment may lead to service failure. Service failures have to be explicitly notified by the applications. Therefore, in this paper we propose a methodology for fault-tolerant coverage planning. The idea is detecting the critical state and removing it by on-line system reconfiguration, and restoration of the original static redundancy. Even in case of a failure the system automatically generates a new configuration to restore the service, leading to shorter repair times. We describe how this approach can be applied to wireless mesh networks, often used in industrial applications like manufacturing, automation and logistics. The evaluation results show that the underlying model used for error detection and system recovery is accurate enough to correctly identify the system state.

Modern real-time applications are very dynamic and cannot cope with the use of worst case execution time to avoid overload situations. Therefore scheduling algorithms that are able to prevent timing faults during overload are required. In this context, the value parameter has become useful to add generality and flexibility to such systems. In this paper, we present the scheduling algorithm called DMB (dynamic misses based), which is capable of dynamically changing tasks value in order to adjust their importance according to its timing faults rate. The main goal of DMB is to allow the prediction of timing faults during overloads and thereby support a dynamic tuning of tasks fault rate. It is used to enhance the features of the previously defined TAFT (time-aware fault-tolerant) scheduler. Obtained results show that DMB in conjunction with TAFT reached the most promising results during overloads, allowing to control tasks degradation in a graceful and determined way

The increasing complexity of current real-time applications demands systems to make good use of the available computational resources. Guaranteeing timing behavior using traditional real-time scheduling policies is turning to be unfeasible, as these policies are based in pessimistic worst-case assumptions that pre-allocate resources even though they will be rarely used. The time-aware fault-tolerant (TAFT) scheduler presents a flexible scheduling strategy that allows the construction of schedules maximizing the CPU utilization. This work presents the use of the TAFT scheduler with computational intensive distributed embedded applications, in order to keep a high ratio of successful tasks completion and so guaranteeing its computational progress. More specifically, the paper sketches a "TAFT-based" fusion algorithm for laser-scanner data and derives the requirements that the execution of this algorithm has on the CPU-scheduling.

Since road networks are the backbone of transportation and personal mobility, congestions are a severe problem. Improving the utilization of existing roads by scheduling shared resources, e.g. crossroads, more efficiently is a promising approach to alleviate the problem. We have developed an architecture allowing mobile systems to schedule shared resource in real-time based on wireless communication. In this paper, we present two membership protocols, which are at the core of this architecture. The protocols allow mobile systems to join and leave a group with predictable delay. A synchronous system model with omission failures describes the dynamic properties of the medium. The protocols exploit application knowledge to allocate bandwidth to joining stations dynamically yet predictably. Nevertheless, they can be converted to a general solution if predictable join delays are not a requirement.

Embedded systems are expected to provide increasingly complex and safety-critical services that will, sooner or later, require the cooperation of several such systems for their fulfillment. In particular, coordinating the access to shared physical and information technological resources will become a general problem. Examples are mobile robots in industrial automation or car-to-car coordination for future traffic control applications. In such applications, cooperation is subject to strong real-time and reliability requirements. In this paper, we present an architecture that allows autonomous mobile systems to schedule shared resources in real-time using their own wireless distributed infrastructure. In this architecture, there is a clear separation between the application-specific scheduling part and the application independent communication part that constitutes the real-time and reliability hardcore of the system. The latter provides clock synchronization, real-time atomic multicast, and real-time group membership based on an IEEE 802.11 standard wireless LAN. An application prototype shows how the architecture can be used in future mobile cooperative applications.

Autonomous systems are expected to provide increasingly complex and safety-critical services that will, sooner or later, require the cooperation of several autonomous systems for their fulfillment. In particular, coordinating the access to shared physical and information technological resources will become a general problem. Scheduling these resources is subject to strong real-time and reliability requirements. In this paper, we present an architecture that allows autonomous mobile systems to schedule shared resources in real-time using their own wireless distributed infrastructure. In our architecture, there is a clear separation between the application-specific scheduling part that is modeled as a function of the global state and the communication part that is used to provide the global state. By isolating the more error-prone communication part within a communication hardcore, the reliability of the overall system is increased and the locally executed scheduling function can be designed with primary focus on the application-specific real-time requirements.

High-precision clock synchronization is one of the most basic requirements in distributed real-time systems. This paper presents an enhanced clock synchronization protocol for wireless local area networks based on the IEEE 802.11 standard. Reducing the time-critical path of the protocol enhances the synchronization precision. As wireless communication links are inherently unreliable, special emphasis is put on fault tolerance. The protocol guarantees high precision even in the presence of message losses. The protocol is implemented in a Windows NT NDIS driver for Lucent WaveLAN cards. For this driver-level implementation, our measurements have shown that a precision of 150 /spl mu/s is achieved.

Object-oriented frameworks have become a key element in the design of distribution systems. They make the existence of the physical and operating system level resources transparent to the designer and provide the abstract view of the distributed systems as a set of objects that interact by invoking well-defined interfaces of each other. Easy reuse of existing components, location transparency and implementation hiding are the main ingredients of such frameworks that simplify the task of designing distributed systems drastically. It is desirable to take advantage of these benefits when designing distributed real-time systems, too. However, this goal conflicts with the essential need to consider the allocation of system resources when real-time requirements must be met. Here, system level resource issues such as execution times on CPUs, thread switches, occurrence of interrupts, and message delays are of primary interest. Our approach to solve this dilemma is to allow and support the designer of distributed real-time object-oriented applications to become aware of system level resources. We present a monitoring tool JewelDC that allows monitoring of distribution activities (i.e. nested sequences of object invocations) in a distributed object-oriented framework. Distributed activities are visualized at the abstract object level while simultaneously revealing their use of system level resources. The tool has been implemented for DCOM on Microsoft Windows NT 4.0.

This paper deals with tolerance to timing faults in time-constrained systems. TAFT (Time Aware Fault-Tolerant) is a recently devised approach which applies tolerance to timing violations. According to TAFT, a task is structured in a pair, to guarantee that deadlines are met (although possibly offering a degraded service) without requiring the knowledge of task attributes difficult to estimate in practice. Wide margin of actions is left by the TAFT approach in scheduling the task pairs, leading to disparate performances; up to now, poor attention has been devoted to analyse this aspect. The goal of this work is to investigate on the most appropriate scheduling policies to adopt in a system structured in the TAFT fashion, in accordance with system conditions and application requirements. To this end, all experimental evaluation will be conducted based on a variety of scheduling policies, to derive useful indications for the system designer about the most rewarding policies to apply.

Continuous clock synchronization avoids unpredictable instantaneous corrections of clock values. This is usually achieved by spreading the clock correction over the synchronization interval. In the context of wireless real time applications, a protocol achieving continuous clock synchronization must tolerate message losses and should have a low overhead in terms of the number of messages. The paper presents a clock synchronization protocol for continuous clock synchronization in wireless real time applications. It extends the IEEE 802.11 standard for wireless local area networks. It provides continuous clock synchronization, improves the precision by exploiting the tightness of the communication medium, and tolerates message losses. Continuous clock synchronization is achieved with an advanced algorithm adjusting the clock rates. We present the design of the protocol, its mathematical analysis, and measurements of a driver level implementation of the protocol on Windows NT.

Designing control and robotic systems as autonomous decentralized systems introduces a new degree of flexibility in the manufacturing and in the application of such systems. This flexibility is required for the systems to work in environments that are not totally predictable and that can change dynamically. In this paper, we present a new concept for real-time communication that supports this flexibility while still preserving real-time guarantees for hard real-time communication. The concept is designed to work on multiple-access busses. In particular we consider its application on wireless local area networks and field-busses. The concept addresses requirements of hard-real time, soft real-time and non real-time communication. For this, we extend the TDMA (time-division multiple-access) approach for time-triggered hard-real time communication by the concept of shared channels that support event-triggered communication and coexist with hard real-time channels. A first implementation of concept has been carried out in the context of the CAN-bus.

This paper describes a powerful integrated development environment that covers all steps of the development of an object-oriented real-time application from initial design to the final evaluation. The system consists of a set of integrated tools for modeling, simulation, implementation, instrumentation, monitoring, and visualization that all work on the same OO system model. As all steps of creating a running implementation with visualized monitoring output from the design model are automatic, the environment encourages an iterative approach to the design of complex real-time control applications. This complete environment has been accomplished by integrating the SIMOO-RT modeling, simulation and implementation environment, developed at the Federal University of Rio Grande do Sul, with the Jewel++ object-oriented instrumentation and monitoring tool from GMD, St. Augustin, Germany. The work has been done in the context of the ADOORATA project (A Distributed Object-Oriented Architecture for Real-Time Automation), a Brazilian-German cooperation.

Real time computing is becoming an enabling technology for many important distributed applications such as flexible manufacturing, multimedia, robotics and process control. Traditionally, real time systems have been realized as isolated embedded systems. Unfortunately, this approach no longer suffices for future complex systems in the application scenarios mentioned above. In this situation, the use of an object oriented design paradigm greatly reduces the complexity of the system while improving reusability and manageability. Furthermore, the surrounding IT infrastructure is more and more accessible through object oriented interfaces (e.g. CORBA). In addition, object oriented modeling allows reflection of the dynamic characteristics of the applications mentioned above by instantiating objects dynamically. In order to meet the real time requirements in such an environment, static scheduling is not sufficient since many non predictable resource conflicts influence execution times. Therefore, the most distinguishing requirement of these complex heterogeneous systems is the need of the computing system to dynamically adapt to dynamically changing conditions. Little work has been done on integrating object oriented system design with resource allocation algorithms that are flexible enough to cope with this new requirement. The paper presents an approach for an adaptive object oriented system with integrated monitoring, dynamic execution time prediction and scheduling. It explains how this approach is applied to CORBA and C++.

A novel and efficient group communication (multicast) protocol, based on a single logical-clock token ring approach, is described. The protocol is highly efficient and it guarantees total ordering and atomicity of multicast messages for asynchronous distributed systems. Unlike other logical token-ring algorithms, the protocol does not have a problem of token loss. The optimized fault-tolerant algorithms of the protocol can handle process failures and network partitioning. The experiment results of the implemented protocol in a local area network of workstations have demonstrated that its performance is better than any existing solutions in the same environment, especially, for achieving message total ordering and atomic (safe) delivery.

Maintaining a consistent state is crucial for cooperative work in autonomous and decentralized systems (ADS). This is achieved through reliable communication protocols in a group of autonomous components. Many existing protocols are quite expensive and not very suitable for the ADS. The paper presents a logical token ring based group multicast protocol for the service of decentralized action manage systems. Unlike previous token based algorithms, we assign a virtual identity to each of the processes executing in the autonomous components in an increasing order so as to form a logical ring. The protocol ensures total ordering and atomicity of multicast messages in the presence of the component failures. The total order is achieved by placing a sequence number in each multicast message. A token process implicitly multicasts one such ordered message and transfers the token to the next process on the ring, hence, reducing the synchronous overhead and preventing possible token lose problem. With a minimal number of control messages, the protocol guarantees that all nonfaulty processes belonging to the same group will observe a consistent view of ordered events affecting all cooperative components in the group. The efficient recovery algorithms can handle the member failures, dynamic groups, group partitions and merges.>

Elements of transaction processing become more and more accepted as a base for fault-tolerant distributed computing. We have developed an action concept with an extended functionality suited to better support the needs of Concurrent Engineering applications. This allows actions to access data produced by other, still active actions. In case of an action fault, however, fault containment may become a problem of major concern. Nesting seems to be an appropriate means to tackle this problem. Unfortunately, it is not possible to simply adopt the nested transactional concept as designed by Moss, because it does not consider dependencies between actions belonging to different parents. This paper is to present a nesting concept which provides an adequate means for fault containment in dynamic actions. Special emphasis is given to the problem of protecting the work of a parent action against the consequences of the abort of other actions.>

Transactions are especially valuable in distributed systems, since they isolate the programmer from the effects of both concurrency and failures. In implementing transactions at the system level, flexibility has to be introduced into the transaction concept. Specifically, the premature release of data objects has to be addressed. To assure recoverability, resulting dependencies between transactions are stored by the system in a distributed data structure called a recovery graph. The storing of redundant information in the recovery graphs at the different sites reduces the complexity of the commit protocol, and a chase protocol used to abort transactions can be derived which excludes infinite chasing. The redundant information can be distributed almost for free because it can be piggybacked on messages. The new commit/abort protocols will be used in the RelaX project (reliable distributed applications support on Unix), which carries on work done at GMD in the PROFEMO project on distributed transaction mechanisms.>

Type-specific locking is designed to increase performance of distributed transactions by allowing competing transactions to concurrently alter shared objects concurrently, provided their changes are commutative. When one of the set of compatible transactions commits or aborts, a problem arises due to the indeterminacy of the alterations of the others. A tree of nineteen solutions to the problem has been investigated. Given the necessary support by the underlying architecture, this tree can be pruned severely. The problem and set of approaches came to the authors' attention during design for type-specific locking in PROFEMO, an operating system for a local area network that provides a location-independent object environment and built-in mechanisms for transaction control and recovery. A description is given of the problem, the possible solutions, and the arguments that allow the pruning. Testbed results are not yet available, since type-specific locking has not yet been implemented at the time of the initial tests of the PROFEMO system.>

The following paper is to present a test and reconfiguration strategy for fault-tolerant VLSI processor systems. This is accomplished with respect to the requirements imposed by the VLSI technology. The proposed concept is exemplified by a model composed of four microprogrammable processors each with a local memory. The test strategy of a gradually expanding hardcore is applied where the central hardcore consists of a small test unit of low complexity. This test unit enables each processor to diagnose autonomously its data path structure and its associated local memory. A particular reconfiguration scheme is proposed for these components. It is implemented at microprogram level. As a result, compared with other fault-tolerance techniques, system reliability is considerably improved.