Minimum time control of large‐scale boolean control networks with constraints

The minimum time control that steers a large‐scale Boolean control network with constraints from an initial state to a given state is investigated. This problem is studied under the partition of the large‐scale Boolean control networks. Based on that, the problem is converted to finding the minimum time control for each subnetwork. Hence, the minimum time control for small size Boolean control networks with constraints is considered firstly. Then, a method to solve the problem for large‐scale Boolean control networks with constraints is presented. Finally, a numerical example on T‐cell receptor kinetics is given to show the effectiveness of the main results.     

Decentralized event‐triggered control of large‐scale nonlinear systems

This paper studies the decentralized event‐triggered control of large‐scale nonlinear systems. We consider a class of decentralized control systems that are transformable into an interconnection of input‐to‐state stable subsystems with the sampling errors as the inputs. The sampling events for each subsystem are triggered by a threshold signal, and the threshold signals for the subsystems are independent with each other for the decentralized implementation. By appropriately designing the event‐triggering mechanisms, it is shown that infinitely fast sampling can be avoided for each subsystem and asymptotic regulation is achievable for the large‐scale system. The proposed design is based on the ISS small‐gain arguments, and is validated by a benchmark example of controlling two coupled inverted pendulums.     

A multi‐GPU algorithm for large‐scale neuronal networks

Large‐scale simulations of parts of the brain using detailed neuronal models to improve our understanding of brain functions are becoming a reality with the usage of supercomputers and large clusters. However, the high acquisition and maintenance cost of these computers, including the physical space, air conditioning, and electrical power, limits the number of simulations of this kind that scientists can perform. Modern commodity graphical cards, based on the CUDA platform, contain graphical processing units (GPUs) composed of hundreds of processors that can simultaneously execute thousands of threads and thus constitute a low‐cost solution for many high‐performance computing applications. In this work, we present a CUDA algorithm that enables the execution, on multiple GPUs, of simulations of large‐scale networks composed of biologically realistic Hodgkin–Huxley neurons. The algorithm represents each neuron as a CUDA thread, which solves the set of coupled differential equations that model each neuron. Communication among neurons located in different GPUs is coordinated by the CPU. We obtained speedups of 40 for the simulation of 200k neurons that received random external input and speedups of 9 for a network with 200k neurons and 20M neuronal connections, in a single computer with two graphic boards with two GPUs each, when compared with a modern quad‐core CPU. Copyright © 2010 John Wiley & Sons, Ltd.     

A heuristic approach for the allocation of resources in large‐scale computing infrastructures

An increasing number of enterprise applications are intensive in their consumption of IT but are infrequently used. Consequently, either organizations host an oversized IT infrastructure or they are incapable of realizing the benefits of new applications. A solution to the challenge is provided by the large‐scale computing infrastructures of clouds and grids, which allow resources to be shared. A major challenge is the development of mechanisms that allow efficient sharing of IT resources. Market mechanisms are promising, but there is a lack of research in scalable market mechanisms. We extend the multi‐attribute combinatorial exchange mechanism with greedy heuristics to address the scalability challenge. The evaluation shows a trade‐off between efficiency and scalability. There is no statistical evidence for an influence on the incentive properties of the market mechanism. This is an encouraging result as theory predicts heuristics to ruin the mechanism's incentive properties. Copyright © 2015 John Wiley & Sons, Ltd.     

Jcluster: an efficient Java parallel environment on a large‐scale heterogeneous cluster

In this paper, we present Jcluster, an efficient Java parallel environment that provides some critical services, in particular automatic load balancing and high‐performance communication, for developing parallel applications in Java on a large‐scale heterogeneous cluster. In the Jcluster environment, we implement a task scheduler based on a transitive random stealing (TRS) algorithm. Performance evaluations show that the scheduler based on TRS can make any idle node obtain a task from another node with much fewer stealing times than random stealing (RS), which is a well‐known dynamic load‐balancing algorithm, on a large‐scale cluster. In the performance aspects of communication, with the method of asynchronously multithreaded transmission, we implement a high‐performance PVM‐like and MPI‐like message‐passing interface in pure Java. The evaluation of the communication performance is conducted among the Jcluster environment, LAM‐MPI and mpiJava on LAM‐MPI based on the Java Grande Forum's pingpong benchmark. Copyright © 2005 John Wiley & Sons, Ltd.     

Energy‐efficient distributed control of large‐scale systems: A switched system approach

This paper is concerned with the sensor‐network‐based distributed control of large‐scale systems with the power constraint. In the underlying system, the measurement is firstly sampled under nonuniform sampling periods, which are varying in a given set. Then, the measurement size reduction technique and communication rate reduction method are used to save the constrained power in sensor networks. Specifically, only one element of sampled measurement is chosen at each sampling time instant, and it is then quantized and transmitted to the neighbouring controllers. Based on the switched system approach, a unified model is presented to capture the nonuniform sampling, the measurement size reduction, the transmission rate reduction and the controller failure phenomenon. A new sufficient condition is obtained such that the filtering error system is exponentially stable in the mean‐square sense with a prescribed H_∞ performance level. Based on this condition, the controller gains are designed by using the cone complementarity linearization algorithm. Finally, a simulation study is given to show the effectiveness of the proposed new design technique. Copyright © 2015 John Wiley & Sons, Ltd.     

Robust estimation‐free decentralized prescribed performance control of nonaffine nonlinear large‐scale systems

In this paper, a low‐complexity robust estimation‐free decentralized prescribed performance control scheme is proposed and analyzed for nonaffine nonlinear large‐scale systems in the presence of unknown nonlinearity and external disturbance. To tackle the high‐order dynamics of each tracking error subsystem, a time‐varying stable manifold involving the output tracking error and its high‐order derivatives is constructed, which is strictly evolved within the envelope of user‐specialized prescribed performance. Sequentially, a robust decentralized controller is devised for each manifold, under which the output tracking error and its high‐order derivatives are proven to converge asymptotically to a small residual domain with prescribed fast convergence rate. Additionally, no specialized approximation technique, adaptive scheme, and disturbance observer are needed, which alleviates the complexity and difficulty of robust decentralized controller design dramatically. Finally, 3 groups of illustrative examples are used to validate the effectiveness of the proposed low‐complexity robust decentralized control scheme for uncertain nonaffine nonlinear large‐scale systems.     

A viable system structure for large‐scale software systems

A homogeneous system structure is proposed that enhances modularity and flexibility, and facilitates (further) development of large‐scale software systems in a major‐industry environment. In our opinion, it is an effective means of countering the inherent increase in software entropy when (further) developing existing large‐scale software systems, thereby substantially cutting down production costs. It can be applied generally both to new and existing systems, whether application programs or operating systems, promotes the parallel use of different programming paradigms and various implementation languages, and offers the option of either redesigning parts or introducing additional parts in stages based on a more modern technology. The proposed system structure is compared and contrasted with other architectures such as CORBA, and it is shown that it may be regarded as an embellishment of the CORBA architecture for the internal structuring or restructuring of possibly distributed software systems. So far it has been used in four releases of the BS2000/OSD operating system with very positive results. Dependencies between various entities – which we call ‘subsystems’ – in the course of the (further) development process, as well as during dynamic execution are minimized and well‐regulated. The subsystems may be loaded on demand during the session by a system authority. Every interface in the system is classified according to its permitted scope of use. For interfaces between subsystems, a uniform and standardized technique is introduced which uses the same format for all implementation languages at both the source‐ and binary‐code level. This technique exceeds the regulations in other architectures but actually achieves considerable rationalization. Copyright © 1999 John Wiley & Sons, Ltd.     

A new family of interconnection and damping assignment passivity‐based controllers

The by‐now standard formulation of interconnection and damping assignment passivity‐based control (for input‐affine systems) proposes the solution of a partial differential equation (PDE) that defines the assignable energy functions and computes the control using the input matrix pseudo‐inverse. However, in its original formulation—a more general design procedure was proposed, which was essentially abandoned because of the difficulties in solving the PDE. In this note, a new family of interconnection and damping assignment passivity‐based controls is proposed by extending this method in the following directions: (i) It allows the desired interconnection and damping matrices to depend on the control signal, giving the possibility to shape the PDE to ensure its solvability; (ii) the PDE directly generates the control signal that have, in general, simpler expressions; and (iii) it is applicable for general nonlinear systems possibly not affine in the control. The technique is illustrated with three examples, including the well‐known boost power converter for which it yields a simple, high‐performance controller. Copyright © 2016 John Wiley & Sons, Ltd.     

Stochastic Analysis of Deterministic Routing Algorithms in the Presence of Self-Similar Traffic

Many performance models for deterministic routing in multicomputer interconnection networks have been derived and analyzed under the assumption of the traditional Poisson stochastic arrival process, which is inherently unable to capture traffic self-similarity revealed by many real-world parallel applications. In an effort towards understanding the network performance under various traffic loads and different design alternatives, this paper presents an analytical model for dimension-ordered routing in k-ary n-cubes when subjected to self-similar traffic. As the service time, blocking probability and waiting time experienced by a message vary from a dimension to another, the design of such a model for dimension-ordered routing poses greater challenges. The developed analytical model is then used to investigate the efficiency of two different ways to organize virtual channels for deterministic routing and to evaluate the impact of self-similar traffic with various Hurst parameters on network performance.     

Decentralized weighted control for a class of large‐scale systems with multi‐modes

In this paper, the control synthesis problem for a class of large‐scale systems with multi‐modes that are called large‐scale switched systems is addressed. By introducing the concept of decentralized switching signal and the relevant decentralized average dwell time, the asymptotic stability and weighted ?₂ gain performance are investigated. It should be noted that the decentralized switching covers general switching cases for large‐scale switched systems, namely, it admits both time‐dependent switching signal and arbitrary switching signal blended in the decentralized switching. Then, on the basis of the analysis results, the decentralized weighted control scheme including state feedback controller gains and switching signals is studied. Several design algorithms are proposed to meet different controller design problems. Finally, numerical examples are provided to illustrate theoretical findings within this paper. Copyright © 2013 John Wiley & Sons, Ltd.     

Adaptive fuzzy output feedback decentralized control of pure‐feedback nonlinear large‐scale systems

In this paper, an adaptive fuzzy decentralized output feedback control approach is presented for a class of uncertain nonlinear pure‐feedback large‐scale systems with immeasurable states. Fuzzy logic systems are utilized to approximate the unknown nonlinear functions, and a fuzzy state observer is designed to estimate the immeasurable states. On the basis of the adaptive backstepping recursive design technique, an adaptive fuzzy decentralized output feedback is developed. It is proved that the proposed control approach can guarantee that all the signals of the resulting closed‐loop system are semiglobally uniformly ultimately bounded (SUUB), and that the observer and tracking errors converge to a small neighborhood of the origin by appropriate choice of the design parameters. Simulation studies are included to illustrate the effectiveness of the proposed approach. Copyright © 2012 John Wiley & Sons, Ltd.     

Control strategies for ventilation networks in small‐scale mines using an experimental benchmark

In view of the frequent ventilation network changes during production in underground mining, decreasing sensors and actuators without altering production control and safety is one of the chief engineering challenges. This work is focused on modeling identification and control strategies for underground ventilation networks in small‐scale mines using an experimental benchmark. Guidelines to obtain a discrete state space model are provided, considering the conservation laws in the network to define the structure of the linear model. The main purpose of the paper is to analyze the use of classic controllers in the mine ventilation system when there are limitations on the number of sensors and actuators available to design a feedback control system. A comparison of three classic control strategies is presented considering the a constraint on the available number of sensors. Experimental and simulation results are presented.     

Adaptive decentralized fault‐tolerant tracking control for large‐scale nonlinear systems with input quantization

In this paper, an adaptive decentralized tracking control scheme is designed for large‐scale nonlinear systems with input quantization, actuator faults, and external disturbance. The nonlinearities, time‐varying actuator faults, and disturbance are assumed to exist unknown upper and lower bounds. Then, an adaptive decentralized fault‐tolerant tracking control method is designed without using backstepping technique and neural networks. In the proposed control scheme, adaptive mechanisms are used to compensate the effects of unknown nonlinearities, input quantization, actuator faults, and disturbance. The designed adaptive control strategy can guarantee that all the signals of each subsystem are bounded and the tracking errors of all subsystems converge asymptotically to zero. Finally, simulation results are provided to illustrate the effectiveness of the designed approach.     

Robust decentralized adaptive fuzzy control for a class of large‐scale MIMO nonlinear systems

In this paper, a novel decentralized robust adaptive fuzzy control scheme is proposed for a class of large‐scale multiple‐input multiple‐output uncertain nonlinear systems. By virtue of fuzzy logic systems and the regularized inverse matrix, the decentralized robust indirect adaptive fuzzy controller is developed such that the controller singularity problem is addressed under a united design framework; no a priori knowledge of the bounds on lumped uncertainties are being required. The closed‐loop large‐scale system is proved to be asymptotically stable. Simulation results confirmed the validity of the approach presented. Copyright © 2011 John Wiley & Sons, Ltd.     

Global decentralized sampled‐data output feedback stabilization for a class of large‐scale nonlinear systems with sensor and actuator failures

In this paper, we investigate global decentralized sampled‐data output feedback stabilization problem for a class of large‐scale nonlinear systems with time‐varying sensor and actuator failures. The considered systems include unknown time‐varying control coefficients and inherently nonlinear terms. Firstly, coordinate transformations are introduced with suitable scaling gains. Next, a reduced‐order observer is designed to estimate unmeasured states. Then, a decentralized sampled‐data fault‐tolerant control scheme is developed with an allowable sampling period. By constructing an appropriate Lyapunov function, it can be shown that all states of the resulting closed‐loop system are globally uniformly ultimately bounded. Finally, the validity of the proposed control approach is verified by using two examples.     

Observer‐based decentralized adaptive control for large‐scale pure‐feedback systems with unknown time‐delayed nonlinear interactions

This paper presents an approximation design for a decentralized adaptive output‐feedback control of large‐scale pure‐feedback nonlinear systems with unknown time‐varying delayed interconnections. The interaction terms are bounded by unknown nonlinear bounding functions including unmeasurable state variables of subsystems. These bounding functions together with the algebraic loop problem of virtual and actual control inputs in the pure‐feedback form make the output‐feedback controller design difficult and challenging. To overcome the design difficulties, the observer‐based dynamic surface memoryless local controller for each subsystem is designed using appropriate Lyapunov‐Krasovskii functionals, the function approximation technique based on neural networks, and the additional first‐order low‐pass filter for the actual control input. It is shown that all signals in the total controlled closed‐loop system are semiglobally uniformly bounded and control errors converge to an adjustable neighborhood of the origin. Finally, simulation examples are provided to illustrate the effectiveness of the proposed decentralized control scheme. Copyright © 2013 John Wiley & Sons, Ltd.     

SubCollaboration: large‐scale group management in collaborative learning

Computer‐supported collaborative learning is a paradigm that uses technology to support collaborative methods of instruction. When combining collaborative learning with the need to exchange documents between students and the teaching staff in a blended learning scenario, version control systems (VCSs) greatly simplify this collaboration. Furthermore, these tools need to be adopted in regular classes as they are used in industrial environments. But deploying a collaborative environment in which version control is used does not scale for large classes. This paper presents SubCollaboration, a platform that uses the VCS Subversion to manage a large number of work spaces in a collaborative learning environment. The tool maintains a reference workspace where teaching staff introduces new material that is then synchronized with the team repositories. Two case studies are presented showing that students easily learn the use of version control and its deployment in large classes is feasible. Copyright © 2010 John Wiley & Sons, Ltd.     

Adaptive fuzzy semi‐decentralized control for a class of large‐scale nonlinear systems with unknown interconnections

In this paper, a general method is developed to generate a stable adaptive fuzzy semi‐decentralized control for a class of large‐scale interconnected nonlinear systems with unknown nonlinear subsystems and unknown nonlinear interconnections. In the developed control algorithms, fuzzy logic systems, using fuzzy basis functions (FBF), are employed to approximate the unknown subsystems and interconnection functions without imposing any constraints or assumptions about the interconnections. The proposed controller consists of primary and auxiliary parts, where both direct and indirect adaptive approaches for the primary control part are aiming to maintain the closed‐loop stability, whereas the auxiliary control part is designed to attenuate the fuzzy approximation errors. By using Lyapunov stability method, the proposed semi‐decentralized adaptive fuzzy control system is proved to be globally stable, with converging tracking errors to a desired performance. Simulation examples are presented to illustrate the effectiveness of the proposed controller. Copyright © 2006 John Wiley & Sons, Ltd.     

A performance model for analysis of heterogeneous multi-cluster systems

This paper addresses the problem of performance modeling for large-scale heterogeneous distributed systems with emphases on multi-cluster computing systems. Since the overall performance of distributed systems is often depends on the effectiveness of its communication network, the study of the interconnection networks for these systems is very important. Performance modeling is required to avoid poorly chosen components and architectures as well as discovering a serious shortfall during system testing just prior to deployment time. However, the multiplicity of components and associated complexity make performance analysis of distributed computing systems a challenging task. To this end, we present an analytical performance model for the interconnection networks of heterogeneous multi-cluster systems. The analysis is based on a parametric family of fat-trees, the m-port n-tree, and a deterministic routing algorithm, which is proposed in this paper. The model is validated through comprehensive simulation, which demonstrated that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions.