Towards Controllable Distributed Real-Time Systems with Feasible Utilization Control

Traditional planning theory considers the general problem of division of labor on computing devices. A fairly large class of planning tasks is included in the described task of resource allocation. The only type of resources in such tasks are computing resources. The article considers the tasks of resource allocation in multi-agent systems, options for their applicability and existing methods of solving these problems. The task of allocating resources is one of the fundamental tasks: from the efficient allocation of one's own time to the distribution between different activities and the tasks of allocating resources in large information systems. The article considers different approaches to resource allocation in large information systems: resource allocation within non-stationary tasks, stationary tasks and in multi-agent systems. These approaches help to solve various applications in real time. In the case of resource allocation in multi-agent systems, their decentralization must be taken into account: agents are directly responsible for themselves and do not have complete information about the system, which changes the very essence of the task. Thus, the development of multi-agent models is possible. The multi-agent scheduling methods used in the system can be used in real-time decentralized systems compared to the previously mentioned traditional methods. Their application provides management of planning and execution of tasks, they can be used to manage groups of objects consisting of a large number of devices and able to quickly process large-scale tasks. Thus, in a short time it is possible to design and commission based on the use of multi-agent technologies for planning new-generation software and hardware systems that can interact and work in a group and applicable to a wide range of tasks in various fields.

Allocation problem has always been one of the fundamental issues of building the applications in real-time computing systems. For real-time applications, the allocation problem should directly address the issues of task and communication scheduling. In this context, the allocation of tasks has to fully utilize the available processors and the scheduling of tasks has to meet the specified timing constraints. Clearly, the execution of tasks under the allocation and schedule has to satisfy the precedence, resources, and other synchronization constraints among them. Recently, the timing requirements of the real-time systems emerge that the relative timing constraints are imposed on the consecutive executions of each task and the inter-task temporal relationships are specified across task periods. In this paper we consider the allocation and scheduling problem of the periodic tasks with such timing requirements. Given a set of periodic tasks, we consider the least common multiple (LCM) of the task periods. Each task is extended to several instances within the LCM. The scheduling window for each task instance is derived to satisfy the timing constraints. We develop a simulated annealing algorithm as the overall control algorithm. An example problem of the sanitized version of the Boeing 777 Aircraft Information Management System is solved by the algorithm. Experimental results show that the algorithm solves the problem in a reasonable time complexity.

This paper reports the detailed parameter space study of the nonlinear dynamical behaviors and their control in a time-delay digital tanlock loop (TDTL). At first, we explore the nonlinear dynamics of the TDTL in parameter space and show that beyond a certain value of loop gain parameter the system manifests bifurcation and chaos. Next, we consider two variants of the delayed feedback control (DFC) technique, namely, the time-delayed feedback control (TDFC) technique, and its modified version, the extended time-delayed feedback control (ETDFC) technique. Stability analyses are carried out to find out the stable phase-locked zone of the system for both the controlled cases. We employ two-parameter bifurcation diagrams and the Lyapunov exponent spectrum to explore the dynamics of the system in the global parameter space. We establish that the control techniques can extend the stable phase-locked region of operation by controlling the occurrence of bifurcation and chaos. We also derive an estimate of the optimum parameter values for which the controlled system has the fastest convergence time even for a larger acquisition range. The present study provides a necessary detailed parameter space study that will enable one to design an improved TDTL system.

Describes a real-time system supporting a tele-surgery application based on the Zeus/sup TM/ system. The application involves performing minimally invasive surgical procedures remotely - i.e. without the surgeon being present in the same room with the patient. Because there is human life at stake, the underlying real-time system must be robust, fail-safe and resilient to communications problems. This paper focuses primarily on the approach taken in communicating between the surgeon-side and patient-side subsystems. In particular, techniques for dealing with the challenges of real-time communications are discussed, e.g. bit errors, packet errors and synchronization. In addition to the control actions and feedback data, several serial data streams are multiplexed, transmitted between one side and the other, demultiplexed, and delivered by the real-time system. These streams have a fundamentally different character from the control actions and feedback values used with the robots. Both types of real-time streams are sent over the same communications link.

As technology scales, the impact of process variation on the maximum supported frequency (FMAX) of individual cores in a MPSoC becomes more pronounced. Task allocation without variation-aware performance analysis can result in a significant loss in yield, defined as the number of manufactured chips satisfying the application timing requirement. We propose variation-aware task allocation for real-time streaming applications modeled as task graphs. Our solutions are primarily based on the throughput requirement, which is the most important timing requirement in many real-time streaming applications. The three main contributions of this paper are: 1) Using data flow graphs that are well-suited for modeling and analysis of real-time streaming applications, we explicitly model task execution both in terms of clock cycles (which is independent of variation) and seconds (which does depend on the variation of the resource), which we connect by an explicit binding. 2) We present two approaches for optimizing the yield. The approaches give different results at different costs. 3) We present exhaustive and heuristic algorithms that implement the optimization approaches. Our variation-aware mapping algorithms are tested on models of real applications, and are compared to the mapping methods that are unaware of hardware variation. Our results demonstrate yield improvements of up to 50% with an average of 31%, showing the effectiveness of our approaches.

A control algorithm using a combined feedback and adaptive control strategy was designed and implemented using digital and analog components. The objective of the controller is to attenuate the vibrations of an open cylinder. The frequency content of the force is broadband noise with a relatively strong harmonic component. Actuation is provided by piezoceramic actuators bonded to the cylinder surface. Both strain and strain rate sensors were developed for this control task. Strain sensing is accomplished by piezoelectric film and piezoelectric ceramic elements bonded to the cylinder. Strain rate sensing is accomplished using distributed piezoelectric film bonded to the cylinder surface together with an interface circuit. Results show that the adaptive controller rejects single frequency vibrations both with and without feedback control. However, by adding an analog feedback control loop, broadband disturbances are attenuated, and the adaptive controller performance is improved. >

The field of active noise control is currently very popular due to the fact that it has many practical applications. Some of these applications include decreasing cabin noise in aircraft and automobiles, reducing noise in rocket payload bays, and minimizing machinery noise in factories. Many researchers have developed active control algorithms for vibrating plates radiating sound into free space or enclosures. Most of the controllers employed have been adaptive like the Filtered-x LMS techniques. Very little previous work has been focused on feedback control techniques. In an earlier paper we have described techniques for controlling sound transmission through rectangular plates radiating into a closed cavity. Robust controllers, based on Linear Quadratic Gaussian with Loop Transfer Recovery (LQG/LTR) methods were designed and implemented on simple test articles. In comparison with LMS algorithm, this robust controller did not perform well. The time delay present in the structural system was not considered in the LQG/LTR design method. Hence, a poor performance was the result. In this paper, we have designed and implemented a modified LQG/LTR controller with time delay on an acoustic chamber test article. This controller estimates the previous states from the present output and predicts states for feedback purposes. The time delay of the structure is compensated in the configuration of the estimator of the controller. We have obtained the simulation and experimental results with the modified controller. The performance of the modified LQG/LTR controller is much better than the LMS controller. The performance of the LMS and LQG/LTR controllers is investigated with respect to change in noise frequency and plant parameter variations. The experimental results are included in this paper.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

This paper introduces a novel lightweight clock synchronization protocol (LCSP) and BUB clock synchronization algorithm based on real-time micro-kernel. Unlike other clock synchronization approaches which rely on redundant exchanged messages, this approach takes advantages of the traffic smoothing technique at each end node to suppress or block other traffics during the clock synchronization duration. The BUB algorithm efficiently decreases the number of synchronization messages exchanged during each synchronization round and can easily extend to large distributed real-time systems. Performance evaluation results prove that the LCSP protocol and the BUB algorithm can provide perfect synchronization precision and are appropriate for most distributed hard real-time and embedded control systems, when integrated with the traffic smoothing technique.

This work presents a detailed study, characterization, and measurement of video latency in a real‐time video streaming application. The target application consists of an automatic control system in the form of a control station and the mini Remotely Operated Vehicle (ROV) equipped with a camera, which is controllable over local area network (LAN) and the Internet. Control signal transmission and feedback measurements to the operator usually impose real‐time constraints on the network channel. Similarly, the video stream, which is required for the normal system control and maneuvering, imposes further strict requirements on the network in terms of bandwidth and latency. Based on these requirements, controlling the system in real time through a standard Internet connection is a challenging task. The measurement of important network parameters like availability, bandwidth, and latency has become mandatory for remotely controlling the system in real time. It is necessary to establish a methodology for the measurement of video and network latency to improve the real‐time controllability and safety of the system as such measurement is not possible using existing solutions due to the following reasons: insufficient accuracy, relying on the Internet resources such as generic Network Time Protocol (NTP) servers, inability to obtain one‐way delay measurement, and many solutions only having support for web cameras. Here, an efficient, reliable, and cost‐effective methodology for the measurement of latency of a video stream over a LAN and the Internet is proposed. A dedicated stratum‐1 NTP server is used and the necessary software needed for acquiring and measuring the latency of a video stream from a generic IP camera as well as integration into the existing ROV control software was developed. Here, by using the software and dedicated clock synchronization equipment (NTP server), it was found that normal video latencies in a LAN were in the range of 488ms – 850ms, while latencies over the Internet were measured to be in the range of 558ms – 1211ms. It is important to note that the values were obtained by using a generic (off‐the‐shelf) IP camera and they represent the actual latencies which might be experienced during control over long range and across international territory borders.

In the last decade, robotic systems have penetrated human life more than human can imagine. In particular, the multi-mobile robotic systems have faced a fast growing due to the fact that by deploying a large collection of mobile robots the overall system has a high redundancy and offers the capability of handling more complex tasks. A group of mobile robots increases robustness against failures and provide flexibility to system changes. In order to achieve a fully autonomous operation, the control algorithm to coordinate the robots becomes more important and decisive. The controller has to meet different requirements that sometimes are conflicting. The main goal of this thesis is to evaluate performance of coordination control algorithms for a group of mobile robots. In the first part of this thesis, a modular framework for simulation and experiments of coordination control of mobile robots is presented. All connections between the modules follow the subscriber/publisher paradigm on the exchanged data, i.e. a component publishes data and other components can subscribe on that data. The data is identified by a named magazine, and actual data packets are called issues of the magazine. By means of simulation and experiments, it is demonstrated how the modularity in the framework allows straightforward modification of system configurations, design parameters, and control algorithms. In the second part, hierarchical coordination control of mobile robots is presented. The hierarchy consists of three layers: a high-level control for motion planning of the robots, a low-level control for motion execution, and a flexible layer to accommodate shifting of responsibilities. One advantage of using a hierarchical approach is the isolation of control design in each layer. Changes in the control strategy of a layer do not necessarily require adaptation of other layers. The proposed control algorithms are used to coordinate a group of unicycle mobile robots that realize the transportation system of an automated warehouse. Using the framework, series of simulations with different design parameters are conducted, as well as real-time experiments. Subsequently, performance analysis of the results is carried out. It is shown that the proposed algorithms are flexible to system changes and scalable to variation in the warehouse demands. The algorithms are robust against failures in the transportation systems. It is found that an algorithm, denoted high-level control, with higher throughputs requires more information sharing between the robots. This algorithm is less robust against failures compared to the algorithm, denoted low-level control, that yields lower throughput. In addition, a cost analysis of the proposed control algorithms is given. It is studied that the cost of realizing the transport using a group of mobile robots, coordinated by the proposed control algorithm, has similar performance-to-cost ratio compared to conveyor systems. This conclusion is very promising having in minds that the proposed control algorithm is not necessarily the optimal one. In the third part, the problem of simultaneous tracking of individual references and formation keeping for a group of mobile robots is investigated. The control algorithm is developed using dynamic feedback linearization. The stability proof is analyzed using the theorem on interconnected systems. Using a root-mean-square-like indicator, the trade off between individual tracking and formation keeping, as well as the influences of communication topologies are analyzed. From the analysis of real-time experiment results, it is found that the best formation keeping is obtained when all robots communicate. As a trade off, this requires a larger communication bandwidth and yields large individual tracking errors. Furthermore, the analysis suggests that to achieve optimal individual tracking and formation keeping simultaneously, there is less need to share information between the robots. In the fourth part, as a complement to the hierarchical control approach, a coordination control algorithm based on Model Predictive Control (MPC) is presented. Focusing on the practical aspects, a sequentially decentralized MPC, i.e. a single MPC computes the control signals of all robots where priority rules are used to determine which robots handled earlier in optimization procedure, is implemented. Using the similar automated warehouse environment, the sequentially decentralized MPC is validated in simulations and real-time experiments. For comparison purposes, a centralized MPC, i.e. a single MPC computes the control signals of all robots, is also implemented. Using completion time as indicators, the influences of the MPC parameters are investigated. It is found that the centralized MPC is better than the sequentially decentralizwed MPC, but with the cost of high computation load and limited number of robots in real-time application. Relevance and performance comparison between the MPC and the hierarchical control approach are presented. It is found that regardless of the control algorithm choices, in terms of completion time, a better performance is obtained when the control algorithm uses information from all robots in computing the control signals.

Boring Bar Chatter Control using Feedback Filtered-x Normalized Least Mean Square Algorithm

This paper proposes feedback control algorithms suitable for the top level of a hierarchical approach to controlling Flexible Manufacturing Systems (FMS). Preview and state feedback control techniques are employed to regulate the inventory levels near zero. The resulting controller utilizes inventory state feedback and anticipatory demand feedforward control, referred to as preview control. The preview control takes on the form of demand filtering. Special dynamic properties of the demand filter are discussed. We show how future demand information is related to present production and inventory levels. Production constraints are explicitly handled in the development of the feedback controller. We present numerical results for a test case.

Embedded parallel and distributed computing systems for real-time applications are becoming commonplace. Many such real-time applications are life-critical and require extensive fault-tolerance capabilities in order to ensure very high reliability. At the same time, cost, power, weight, and volume constraints require that any introduced redundancy must be efficiently used. Thus, failure-recovery strategies must be implemented to allow the system to most efficiently manage its resources in the presence of one or more failures, while attempting to continue the execution of the current tasks so as to not miss any deadlines. We have developed such a resource-management algorithm, which selects the optimal failure recovery procedure to be employed when a processor failure is detected. Further, in order to test this and other possible recovery algorithms, we have developed the RAPIDS simulator testbed. This paper describes the testbed, and shows how it provides a framework in which to simulate distributed real-time systems. In addition we describe how RAPIDS allows the user to validate fault recovery algorithms.

Real-time systems are increasingly used in applications whose failure may result in large economic and human costs. Since many such systems operate in environments that are non-deterministic, and possibly hazardous, it is extremely important that the systems be dependable, namely the deadlines of tasks must be met even in the presence of particular failures. In order to enhance the dependability of a real-time system, we study the problem of scheduling a set of real-time tasks to meet their deadlines in the presence of processor failures. We first prove that the problem of scheduling a set of non-preemptive tasks on more than two processors to tolerate one arbitrary processor failure is NP-complete even when the tasks share a common deadline. Heuristic algorithms are then proposed to solve this problem. The schedules generated by the heuristic algorithms can tolerate one arbitrary processor failure in the worst case. The analysis and experimental data show that the performance of the algorithms is near-optimal.

One way to manage the complexity of the design and the implementation of large and adaptive real-time systems is to partition the design into modes of operation. This approach allows designers to break down the complexity of these systems into a number of layers of control (modes), which are then multiplexed in time (by means of mode changes) during system operation. However, due to a lack of a uniform view of modes within the literature, the task of successfully designing complex real-time systems with modes of operation becomes more difficult, if not compromised [1]. In this paper we consider the following recurring issues of modes in real-time systems, both from the application and design concerns: 1) What is a mode of operation, i.e. which features are exclusive to a particular mode of operation that allow its identification and distinction from other modes? 2) What can be understood by the concept of mode changes in realtime systems? The examination of these issues is lacking in the literature and will facilitate the analysis, design and construction of the next generation of complex real-time systems.