In many cases, demands of Intelligent Manufacturing are generated locally and served locally, not necessarily dependent on the cloud. We believe in the distributed intelligent production system, cloud and edge systems should act as equal processing nodes for service migration and cooperation. This paper focuses on the edge nodes and expands the scope of edge computing, aimed at building an independent and complete edge system - DEPS based on demand-orientation. To adapt to the edge environment, DEPS adopts a hierarchical structure to provide a relatively complete system framework for multiple parallel services. To meet the demands of industrial production, DEPS takes two measures: 1) integrates a variety of existing industrial control systems; 2) uses flexible modular design to allow experts to participate in the design, enhancing the professionalism of the system which can be designed more on-demand. We use short and continuous industrial production data to evaluate DEPS and propose a method to measure its processing performance versus current systems: 1) as for a cloud only system, DEPS has superior performance servicing local demands in real-time, securely and of lower cost; 2) as for current edge systems, partial comparison of them in applications and performances is discussed.

In the field of bearing fault diagnosis, it is difficult to obtain a large amount of labeled data for training, and therefore it is easy to overfit the model, which makes it less robust and less generalizable. To address this problem, this article offers a novel semi-supervised contrastive learning (SSCL) method based on a multiscale attention (MSA) mechanism and multitarget contrastive learning (MCL) for rolling bearing fault diagnosis under limited labeled samples. First, the proposed SSCL utilizes improved MCL to pretrain the model as a means of capturing potentially generic features in unlabeled data. Then, semi-supervised contrast learning is constructed and based on the pretrained model combining a limited amount of labeled data and a large amount of unlabeled data to jointly learn the feature mapping and further enhance the feature extraction capability of the model through an MSA mechanism. Case Western Reserve University, the Society for Mechanical Failure Prevention Techniques, and Paderborn University are common motor-bearing datasets that are used in this article for testing the proposed technique. As a result of the experimental findings, SSCL is demonstrated to be superior to other approaches in similar situations.

Van Genuchten (VG) equation is the most commonly used equation of soil moisture characteristic curve, and the accuracy of its parameters directly affects the calculation accuracy of soil moisture motion equation. In order to obtain the parameters of the equation more accurately, this paper establishes an optimization model of the VG equation parameters. This optimization model uses the advantages of the cuckoo search algorithm and the differential evolution algorithm to combine the two into a new hybrid cuckoo search algorithm, namely DECS algorithm, and uses this algorithm to solve the parameter optimization problem of VG equation of soil moisture characteristic curve. By collecting and analyzing the relevant experimental data of various soil qualities, the dehumidification and moisture absorption curves of three different soil qualities were selected for simulation calculation. The results show that in the experiment of solving the parameter estimation problem of the VG equation, the DECS hybrid algorithm has better exploration and development capabilities than the cuckoo search algorithm. The hybrid algorithm has relatively significant performance in terms of calculation accuracy and convergence.

We address a special kind of Internet of Things (IoT) systems that are also real-time. We call them real-time IoT (RT-IoT) systems. An RT-IoT system needs to meet timing constraints of system delay, clock synchronization, deadline, and so on. The timing constraints turn to be more stringent as we get closer to the physical things. Based on the reference architecture of IoT (ISO/IEC 30141), the RT-IoT conceptual model is established. The idea of edge subsystem is introduced. The sensing & controlling domain is the basis of the edge subsystem, and the edge subsystem usually must meet the hard real-time constraints. The model includes four perspectives, the time view, computation view, communication view, and control view. Each view looks, from a different angle, at how the time parameters impact an RT-IoT system.

Wireless sensing and networking technologies have taken a strong foothold in the process control industry. The focus has now shifted towards applying control with wireless technology. As such, the current industrial wireless sensor network architectures are under increased scrutiny about their real-time, reliability, and security performances. In this paper, we take a renewed look at network synchronization, the basic building block to support real-time activities. We present our analysis, key observations, and recommendations. We also get into the depth of WirelessHART, the most deployed industrial wireless network architecture, and affirm that, with good practice, we could achieve highly reliable synchronization to provide guaranteed packet deliveries. The correctness of the time synchronization analysis in both line and mesh network topologies is verified through extensive simulation experiments.

Real-time wireless sensor networks in the industrial settings usually consist of tens of nodes. Seldom do we see a network of over 100 wireless nodes. The smaller size is usually sufficient as a typical plane unit is no larger than a football field size, and the critical data points of interest are not many. We believe, however, there is need for large scale real-time wireless sensor networks. In this paper we shall use WirelessHART as the platform to study and build one. We shall study the possibility, propose the methods to achieve, and test our solutions with experimentations.

Maintaining the freshness of real-time data is one of the crucial design issues in cyber-physical systems (CPS). Past studies have focused on designing update algorithms to minimize the workload imposed by a fixed set of update tasks while ensuring the temporal validity of data. In this paper, we revisit this problem in dynamic cyber-physical systems (DCPS) which may exhibit multi-modal behavior. Any solution to this problem must recognize that: (1) different update algorithms may be needed in different modes according to the workload in each mode, and (2) temporal validity of data must be maintained not only in each mode but also during the mode switch. To strike a balance between data freshness and system schedulability, we propose a utilization-based scheduling selection (UBSS) strategy. We first introduce two synchronous mode switch algorithms, named search-based switch (SBS) and adjustment-based switch (ABS) to search for the proper switch point online and execute all update tasks in the new mode synchronously. SBS checks for temporal validity at the beginning time slot of each idle period in the schedule, while ABS relaxes this restriction through schedule adjustment. To support immediate mode switch, we propose an asynchronous switch algorithm named instant switch (IS) to reduce the switch delay. IS schedules outstanding jobs from the old mode together with the jobs in the new mode using the least-available-laxity-first scheduling policy. Our experimental results demonstrate the effectiveness of these three algorithms. They also show that UBSS strategy can significantly outperform a single fixed update algorithm in terms of maintaining better data freshness while incurring only limited online switch overhead.

Although the deferrable scheduling algorithm for fixed priority transactions ( DS-FP) has been shown to provide a better performance compared with the More-Less (ML) method, there is still a lack of any comprehensive studies on the necessary and sufficient conditions for the schedulability of DS-FP. In this paper, we first analyze the necessary and sufficient schedulability conditions for DS-FP, and then propose a schedulability test algorithm for DS-FP by exploiting the fact that there always exists a repeating pattern in a DS-FP schedule. To resolve the limitation of fixed priority scheduling in DS-FP, we then extend the deferrable scheduling to a dynamic priority scheduling algorithm called DS-EDF by applying the earliest deadline first (EDF) policy to schedule update jobs. We also propose a schedulability test for DS-EDF and compare its performance with DS-FP and ML through extensive simulation experiments. The results show that the schedulability tests are effective. Although the schedulability of DS-EDF is lower than DS-FP and the repeating patterns in DS-EDF schedules are longer than those in DS-FP due to the use of dynamic priority scheduling, the performance of DS-EDF is better than both DS-FP and ML in terms of CPU utilization and impact on lower priority application transactions.

Localization in wireless sensor networks is an important functionality that is required for tracking personnel and assets in industrial environments, especially for emergency response. Current commercial localization systems such as GPS suffer from the limitations of either high cost or low availability in many situations (e.g., indoor environments that exclude direct line-of-sight signal reception). The development of industrial wireless sensor networks such as WirelessHART provides an alternative. In this article, we present the design and implementation of ColLoc: a collaborative location and tracking system on WirelessHART as an industrially viable solution. This solution is built upon several technological advances. First, ColLoc adds the roaming functionality to WirelessHART and thus provides a means for keeping mobile WirelessHART devices connected to the network. Second, ColLoc employs a collaborative framework to integrate different types of distance measurements into the location estimation algorithm by weighing them according to their precision levels. ColLoc adopts several novel techniques to improve distance estimation accuracy and decreases the RSSI presurvey cost. These techniques include introducing distance error range constraints to the measurements, judiciously selecting the initial point in location estimation and online updating the signal propagation models in the anchor nodes, integrating Extended Kalman Filter (EKF) with trilateration to track moving objects. Our implementation of ColLoc can be applied to any WirelessHART-conforming network because no modification is needed on the WirelessHART field devices. We have implemented a complete ColLoc system to validate both the design and the effectiveness of our localization algorithm. Our experiments show that the mobile device never drops out of the WirelessHART network while moving around; with the help of even one dependable anchor, using RSSI can yield at least 75% of distance errors below 5 meters, which is quite acceptable for many typical industrial automation applications.

The Internet of Things (IoT) is considered to be the biggest challenge and opportunity for the Internet today. The Internet of Things makes it possible to connect embedded devices in physical environments to the Internet and interact with those devices through both IP and web interfaces. As a subset of the Internet of Things, the wireless embedded Internet targets at enabling resource-limited wireless devices with IP functions and connecting them to the Internet through low-power and low-bandwidth wireless networks. In this paper, we describe our design of the network infrastructure of wireless embedded Internet for industrial automation, and present the implementation and demonstration of a prototype system which integrates WirelessHART mesh networks into the Internet and supports web-based monitoring and control services.

WirelessHART™ was released in September 2007 and became an IEC standard in April 2010 (IEC 62591). It is the first open wireless communication standard specifically designed for process measurement and control applications deployed in harsh and noisy environments. WirelessHART distinguishes itself from other public standards by maintaining a central Network Manager. The Network Manager is responsible for maintaining up-to-date routes and communication schedules for the network, thus guaranteeing the reliable and real-time network communications. To deal with the intensive computation requirement in a centralized WirelessHART Network Manager, particularly of middle or large scale network sizes, in this article, we utilize parallelization techniques to implement the Network Manager on embedded multicore architectures. By leveraging the multicore capabilities of the AMD Embedded G-Series Dual-Core processor, we utilize the Texas Multicore Technologies' (TMT) SequenceL™ language and runtime environment to parallelize the algorithms proposed in our previous work for constructing reliable routing graphs and real-time communication schedule. Our experiments show that AMD Embedded G-Series is an ideal platform for medium to large size WirelessHART network and SequenceL™ language can help significantly reduce the development cycle and further improve the algorithm efficiency and system performance in embedded multicore architectures.

Wireless applications in process automation started in areas where wireless sensors provide rich process information to the automation systems. Shortly after WirelessHART became the international standard, both ISA100.11a and WirelessHART claimed that their respective wireless technology could be applied to control as well. Although both standards provide provisions for supporting control over wireless, actual installations of wireless control systems have been slow to be adopted. Due to people's wariness of using wireless in combination with the serious nature of control, what is needed is a demonstration of performance and reliability of control when being executed across wireless media. A good starting point is a comparison between a wireless control system and its wired counterpart. In this paper we first study if we can establish a WirelessHART control loop the same way as a wired one; then we study if our WirelessHART control loop could achieve the same execution rates and reliability as a wired Foundation Fieldbus control loop. The experiment affirms that, in most likely cases, control over a WirelessHART network could be as good as control over a wired fieldbus.

Localization in wireless sensor networks is an important functionality that is required for tracking personnel and assets in industrial environments, especially for emergency response. Current commercial localization systems such as GPS suffer from the limitations of either high cost or low availability in many situations (e.g., in-door environments that exclude direct line-of-sight signal reception). The development of industrial wireless sensor networks such as Wireless Hart provides an alternative. In this paper, we present the design and implementation of Roaming Hart: a collaborative localization system on Wireless Hart as an industrially viable solution. This solution is built upon several technological advances. First, Roaming Hart adds the roaming functionality to Wireless Hart and thus provides a means for keeping mobile Wireless Hart devices connected to the network. Second, Roaming Hart employs a collaborative framework to integrate different types of distance measurements into the location estimation algorithm by weighing them according to their precision levels. Roaming Hart adopts several novel techniques to improve distance estimation accuracy and decreases the RSSI pre-survey cost. These techniques include introducing distance error range constraints to the measurements, judiciously selecting the initial point in location estimation and on line updating the signal propagation models in the anchor nodes. Our implementation of Roaming Hart can be applied to any Wireless Hart-conforming network because no modification is needed on the Wireless Hart field devices. We have implemented a complete Roaming Hart system to validate both the design and the effectiveness of our localization algorithm. Our experiments show that the mobile device never drops out of the Wireless Hart network while moving around, with the help of even one dependable anchor, using RSSI can yield at least 75% of distance errors below 5 meters, which is quite acceptable for many typical industrial automation applications.

The traditional sampling method in process control systems is based on a periodic task model. This is because controllers are executed in a strictly periodic manner. Sensors sample the process data and send it periodically to the appropriate controllers through a communication system such as the field bus. Since the field bus is shared by multiple sensors, there is some delay (control loop latency)between the sampling and control actions. In order to minimize the control loop latency, a higher than necessary sampling frequency is typically adopted, which results in unnecessary waste of energy. In this paper, we propose Min Max: a sampling interval control algorithm for tackling this problem. In Min Max, sampling tasks are not periodic but have both maximum and minimum distance constraints. This sampling model has advantages that are especially important in the domain of wireless control for industrial automation. We shall then discuss the jitter property of sampling schemes under this model and propose algorithms for controlling the sampling intervals of sensors in terms of the Min Max problem (UMin Max) which we shall introduce. Though this problem is NP-hard in general, even for special case of unit-time tasks, we show how to reduce Min Max to well-studied scheduling models such as Liu and Layland-type periodic models and pinwheel models, at the expense of some loss of schedulability. These reductions allow us to derive efficient schedulability tests that can be used to solve the sampling interval control problem in practice. Simulations are used to compare the performance of different UMin Max schedulers in two key figures of merit: the acceptance ratio and the jitter ratio. Simulation of a process control system model also shows that UMin Max can reduce about 40% of the traffic load on the communication system which is especially important for energy-aware wireless process control applications.

In this paper, we report on the design and implementation of MBStar, a higher-frequency, real-time, reliable, secure protocol for wireless body area networks (WBAN). As in most proposals for body sensor networks, MBStar adopts the star topology for communication, and is designed to support a message rate as high as 400 Hz, which to the best of our knowledge, is the highest among low-power wireless communication protocols implemented at the present time. The physical layer of MBStar utilizes 802.15.4 DSSS compatible radio for which a higher-frequency, reliable, TDMA MAC layer is built. There is a simple application layer designed for security on top of it. MBStar utilizes public/private key encryption for provisioning devices and does not involve any human configuration before device join. Considering the resource limit of most embedded systems, the TDMA requirement of computing a shared global communication schedule presents a practical problem since it may not be feasible for all the devices to communicate in a long hyper-period while the communication schedule between devices is being created or modified as devices depart and rejoin. We solve this problem by keeping only the global hyper-period schedule on the gateway side, with each device being configured with a shorter, local period. Then, retransmission is employed to resolve any conflicts between the devices. Our strategy has the property that, given any fixed task set, the minimal average number of retransmissions is independent of any communication scheduling algorithm, and the EDF (Earliest Deadline First) is optimal for our communication architecture. Finally, we present experimental results that demonstrate that MBStar is an effective protocol for wireless body area networks.

Industrial wireless mesh networks are deployed in harsh and noisy environments for process measurement and control applications. Compared with wireless community networks, they have more stringent requirements on communication reliability and real-time performance. Missing or delaying of the process data by the network may severely degrade the overall control performance. In this paper, we abstract the primary reliability requirements in typical industrial wireless mesh networks and define three types of reliable routing graphs for different communication purposes. We present efficient algorithms to construct them and describe the recovery mechanisms in the event of component failures. Based on these graphs, data link layer communication schedules are generated to achieve end-to-end real-time performance. We demonstrate through extensive experimental results that our algorithms can achieve highly reliable routing, improved communication latency and stable real-time communication in large-scale networks at the cost of modest overhead in device configuration.

Unlike wired networks, the configuration and the behavior of wireless networks are heavily dependent on many environmental factors. While this makes it more difficult to build a wireless network testbed whose behavior is controllable, it also makes the availability of such a testbed all the more desirable. Indeed, the difficulties in building a good wireless mesh testbed belie the fact that most research work on mesh network performance is backed up only by computer simulations. In this paper, we present a practical design philosophy in which a realistic and controllable wireless mesh network testbed is built with a relatively small deployment of physical equipments by exploiting the idea of a virtual network. Specifically, we simulate a virtual network within the testbed and use one physical wireless transceiver to simulate multiple virtual devices. An observer who only reads the transmitted wireless messages will not be able to tell the difference from a real wireless mesh. Our approach has been adopted in a recent industry-standard testing suite, namely, Wi-HTest. In this paper, we shall discuss our experience in building Wi-HTest by applying the virtual network approach.

WirelessHART was released in September 2007 and is the first open wireless communication standard specifically designed for real-time process control applications. It is designed to the same standards as its wired counterpart for reliability and interoperability. To ensure the compliance with the HART Communication Protocol and the adherence to its strict timing requirements, all WirelessHART devices must be thoroughly tested and registered with the HART Communication Foundation (HCF). In this paper, we present Wi-HTest, the test suite designed to exercise WirelessHART devices, thus facilitating compliance assessment. We discuss the detailed architecture of Wi-HTest and highlight several critical features like packet handling with accurate timing control and fault data injection. We also describe a sniffer called Wi-Analys for capturing WirelessHART packets along with their timing information and a post process suite for analyzing the packets. These three tools together provide the complete compliance verification environment for WirelessHART. Based on the test specification developed by HCF, a representative test case is conducted for the purpose of demonstration. This test case in turn shows that Wi-HTest is a novel and efficient test suite for verifying the compliance of real-time WirelessHART devices.

WirelessHART is an emerging wireless communication standard that is targeted at the real-time process control industry.An example application of wireless communication in an industrial process control plant is the location of field engineers. The capability to locate personnel is a safety critical issue in process control plants because of high risks posed by toxic chemicals and other hazards. This paper presents the design, implementation and evaluation of a location-aware application built upon WirelessHART. The aim of this application is to locate a mobile device (and thus the person carrying the device) via the deployed WirelessHART network. The application is a software-based - no device modifications are required. Consequently, it is applicable to any WirelessHART network. In this application, both the mobile device (a handheld device or a badge carried by a worker) and field devices (attached to the plant process) periodically send health reports of their neighbors to the network manager. The network manager analyzes these reports and discards the untrustworthy pairs through comparison. Next, the network manager feeds the average received signal indications to a well-trained radio propagation model to derive the location. To evaluation our solution, several preliminary experiments are carried out and the results are very promising, with a median error less than 4 meters, which is good enough for the industrial requirement. To the best of our knowledge, this is the first attempt to develop location-aware application in WirelessHART networks.

Maintaining the temporal validity of real-time data is one of the crucial issues in a real-time database system. Past studies focus on designing algorithms to minimize imposed workload by a fixed set of update transactions while maintaining data freshness within validity intervals. In this paper we revisit this problem by investigating the cost of data freshness maintenance and online scheduling overhead in the presence of mode changes in real-time systems. We propose to apply periodic scheduling policies when the imposed update workload is low to maintain high data freshness. When the update workload becomes high, we propose to switch to more sophisticated algorithms to improve schedulability. In the latter case, not only each scheduling policy must be able to schedule the task set in the corresponding mode, temporal validity must also be maintained during the mode changes. To address this problem, two algorithms, named search-based switch (SBS) and adjustment-based switch (ABS) are proposed to search for the proper switch point online. SBS checks the temporal validity at the beginning time slot of each idle period while ABS further relaxes this restriction through schedule adjustment. Our experimental results demonstrate the correctness and efficiency of these two algorithms. Our results also show that scheduling switch according to the runtime processor workload can significantly outperform a single fixed scheduling policy in terms of data freshness while incurring only limited online switch overhead.

The schedulability testing for the deferrable scheduling algorithm for fixed priority transactions (DS-FP) remainsan open problem since its introduction. In this paper, wetake the first step towards investigating necessary and sufficient conditions for the DS-FP schedulability. We propose a necessary and sufficient schedulability condition for the algorithm in discrete time systems, and prove its correctness. Based on this condition, we propose a schedulability test algorithm that is more accurate than the existing test that is only based on a sufficient condition. Our algorithm exploits the fact that there is always a repeating pattern in a DS-FP schedule in discrete time systems. We demonstrate through examples that our schedulability test algorithm outperforms the existing algorithm in terms of accuracy.

Wireless technology has been regarded as a paradigm shifter in the process industry. The first open wireless communication standard specifically designed for process measurement and control applications, WirelessHART was officially released in September 2007 (as a part of the HART 7 Specification). WirelessHART is a secure and TDMA-based wireless mesh networking technology operating in the 2.4GHz ISM radio band. In this paper, we give an introduction to the architecture of WirelessHART and share our first-hand experience in building a prototype for this specification. We describe several challenges we had to tackle during the implementation, such as the design of the timer, network wide synchronization, communication security, reliable mesh networking, and the central network manager. For each challenge, we provide a detailed analysis and propose our solution. Based on the prototype implementation, a simple WirelessHART network has been built for the purpose of demonstration. The demonstration network in turn validates our design. To the best of our knowledge, this is the first reported effort to build a WirelessHART protocol stack.

WirelessHART was released in September 2007 and is the first open wireless communication standard specifically designed for process control applications. As an optional part of the HART® Communication Protocol, WirelessHART is designed to the same standards for reliability and interoperability. To ensure the compliance and adherence to the high level of interoperability defined by the HART Communication Foundation (HCF), all WirelessHART devices must be thoroughly tested and registered with the HCF. In this paper, we present Wi-HTest, the test engine designed to exercise WirelessHART devices, thus facilitating compliance assessment. We discuss the detailed architecture of Wi-HTest and highlight several critical features like virtual devices and fault data injection.

WirelessHART is the first open wireless standard for the process control industry. Previously we demonstrated a three-node prototype network based on an early release of the protocol stack. In this demonstration we build a fully operational WirelessHART sensor network of multiple nodes. We show the creation of the network and the execution of process monitoring applications on the network. This new demonstration network serves as a proof of concept for the revised WirelessHART standard and as a platform for our future research and experiments.

The periodic update transaction model has been used to maintain the freshness (or temporal validity) of real-time data. Period and deadline assignment has been the main focus of past studies, such as the More-Less scheme [25], in which update transactions are guaranteed by the Deadline Monotonic scheduling algorithm [16] to complete by their deadlines. In this paper, we propose a deferrable scheduling algorithm for fixed-priority transactions, a novel approach for minimizing update workload while maintaining the temporal validity of real-time data. In contrast to prior work on maintaining data freshness periodically, update transactions follow an aperiodic task model in the deferrable scheduling algorithm. The deferrable scheduling algorithm exploits the semantics of temporal validity constraint of real-time data by judiciously deferring the sampling times of update transaction jobs as late as possible. We present a theoretical estimation of its processor utilization and a sufficient condition for its schedulability. Our experimental results verify the theoretical estimation of the processor utilization. We demonstrate through the experiments that the deferrable scheduling algorithm is an effective approach and it significantly outperforms the More-Less scheme in terms of reducing processor workload.

Wireless sensor networks have been a very active research field in the past few years. However, most of extant research has focused on wireless sensing, such as environmental and habitat monitoring [6]. In this paper, we investigate the feasibility of applying wireless technologies in industrial real-time process control systems. We define a minimum set of assumptions about the underlying sensor networks in order to achieve realtime support for process control. These assumptions are necessary and practical from an industrial perspective. We formulate the modeling of a wireless process control configuration as a multi-processor scheduling problem. The resulting scheduling problem is solved by the scheduler synthesis tool MSP.RTL [7] to produce a valid configuration for deployment. The deployment, because of the way it is derived, will provide real-time wireless support for the controlled processes. Simulation results on data from real plant configurations show that this approach can also drastically reduce potential interferences between wireless transfers.

The deferrable scheduling algorithm for fixed priority transactions (DS-FP) is demonstrated to be a very effective approach for minimizing real-time update transaction workload while maintaining temporal validity of real-time data. This paper examines the schedulability of deferrable scheduling and presents a sufficient condition. While its online scheduling overhead is a concern, we propose a hyperperiod based DS-FP approach satisfying the temporal validity constraint with low overhead. The algorithm, namely DEferrable Scheduling with Hyperperiod by Schedule Adjustment (DESH-SA), adjusts the DS-FP schedule in an interval so that the adjusted schedule in the interval can be repeated infinitely. Our experiments demonstrate that DESH-SA can reduce scheduling overhead of DS-FP and also achieve update workload near optimal

In a wireless sensor network, a sensor measures environmental data. It also relays data for other sensors. While sensing workload is the same among sensors, relaying workload differs. Sensors closer to the data sink carry more data traffic. This becomes more prominent as the network scales up. The drawback of this is that nodes in the network degrade unevenly and the network ages in a non-uniform way. This paper seeks the ways to deploy the network so that the workload is evenly distributed, thus the network overall behavior degrades in a smooth fashion. Assuming that the sensors should be evenly deployed within the monitored area, we look at the approach where a set of more powerful nodes are designated for data relaying. We look at the approach to deploy relaying nodes that are easy to implement in practice. In particular, we select sub-regions to deploy relaying nodes at calculated density. We propose a simple method where the density is simply based on the size of the area whose data is relayed by these nodes.

In a pure sensor network thousands of sensors are distributed over a large area. Sensor data is relayed from sensor node to node until it reaches the edge node, where it is then routed by wire to the host. In this paper we study the effect of data collection on the battery and buffer of a sensor node, and on the overall sensor network. We determine the relationship among battery life, sampling frequency, buffer size, etc. We claim that using identical sensors throughout a large scale sensor network may not achieve the best result. We suggest some guidelines for deploying a large scale sensor network. We then propose routing algorithms that are robust, truly distributed, and efficient in utilizing the sensor network.

A real-time task usually generates data. The study on real-time tasks either ignores this fact like most of the research do, or models data as execution time like when handling multimedia data. On the other hand, the network research community usually pays little attention to the data source other than assuming certain characteristics. There are many real world applications where data is not generated at a constant rate during task execution, and the average data rate is not the same among tasks. In this paper we study a new task model with data output as an explicit parameter. We analyze the data output of such task set. We shall derive the data source parameters assumed by network studies. Different scheduling policy results in different data output curve, we look at this in detail with simulations. Our work extends the real-time research to cover a new set of real world applications; it also complements the network study on data transmission.

The multiframe model of hard-real-time tasks is a generalization of the well-known periodic task model of C. Liu and J. Layland (1973). The feasibility analysis of systems of multiframe tasks which are assigned priorities according to the rate-monotonic priority assignment scheme is studied. An efficient sufficient feasibility test for such systems of multiframe tasks is presented and proved correct-this generalizes a result of A.K. Mok and D. Chen (1997).

The concept of data similarity was introduced by T.-W. Kuo and A.K. Mok (1996) to capture the semantics of real time applications where the consistency requirement of a transaction can be relaxed modulo a binary relation on the data space. Even though the notion of data similarity is naturally suited to many applications in the process control industry, its adoption is hampered by the lack of an easy interface to COTS (commercial-off-the-shelf) components. We report our ongoing work in incorporating the idea of data similarity into embedded applications, especially in the process control industry. Our approach is to allow designers to specify similarity predicates by means of an SQL-like interface to the client applications. Query processing is performed by a compact firm-real-time database engine called SRDE (Similarity-based Real-time Database Engine). SRDE is object oriented and is designed to manage real-time data efficiently in a distributed environment. By exploiting data similarity, SRDE can be used to minimize data traffic according to the client's specifications. SRDE has been implemented in 100% JAVA that supports JDBC API. We demonstrate the use of SRDE in a typical industrial control application.

A model for periodic tasks is proposed that explicitly incorporates jitter-the uncertainty in the arrival times of individual frames. Feasibility-analysis of systems of such tasks is studied in the context of dynamic-priority, preemptive, uniprocessor scheduling. From a computational complexity perspective, the problem is shown to be no more difficult than feasibility analysis in systems of periodic tasks that do not exhibit jitter. Several feasibility analysis algorithms are presented and proven correct.

The well known periodic task model of C.L. Liu and J.W. Layland (1973) assumes a worst case execution time bound for every task and may be too pessimistic if the worst case execution time of a task is much longer than the average. We give a multiframe real time task model which allows the execution time of a task to vary from one instance to another by specifying the execution time of a task in terms of a sequence of numbers. We investigate the schedulability problem for this model for the preemptive fixed priority scheduling policy. We show that a significant improvement in the utilization bound can be established in our model.

The well-known periodic task model of Liu and Layland (1973) assumes a worst-case execution time bound for every task and may be too pessimistic if the worst-case execution time of a task is much longer than the average. We give a multiframe real-time task model which allows the execution time of a task to vary from one instance to another by specifying the execution time of a task in terms of a sequence of numbers. We investigate the schedulability problem for this model for the preemptive fixed priority scheduling policy. We show that a significant improvement in the utilization bound can be established in our model.