Flexibility and coordination in event-based,loosely coupled,distributed systems

The scale and diversity of interactions in current wide-area distributed programming environments, specially in Internet-based applications, point to the fact that there is no single solution for coordinating distributed applications. Instead, what is needed is the ability to easily build and combine different coordination abstractions. In this paper, we discuss the role of some language features, such as first-class function values, closures, and coroutines, in allowing different coordination mechanisms to be constructed out of a small set of communication primitives, and to be easily mixed and combined. Using the Lua programming language, we define a basic asynchronous primitive, which allows programming in a direct event-driven style with the syntax of function calls, and, based on this primitive, we build different well-known coordination abstractions for distributed computing.     

Rollback recovery in distributed systems using loosely synchronizedclocks

A rollback recovery scheme for distributed systems is proposed. The state-save synchronization among processes is implemented by bounding clock drifts such that no state-save synchronization messages are required. Since the clocks are only loosely synchronized, the synchronization overhead can be negligible in many applications. An interprocess communication protocol which encodes state-save progress information within message frames is introduced to checkpoint consistent system states. A rollback recovery algorithm that will force a minimum number of nodes to roll back after failures is developed     

Distributed cognition in Search and Rescue: loosely coupled tasks and tightly coupled roles

The perceptual cycle model (PCM) underpins much Ergonomics research, particularly in a team context, for example in its theoretical underpinning of distributed situation awareness. Despite this, the PCM framework it has not been explicitly applied to explore team processes, which is surprising given the prevalence of teamwork in safety critical systems. This paper explores team processes in the context of search and rescue (SAR) by applying the PCM and an association classification scheme with a network analysis approach utilising the event analysis of systemic teamwork (EAST) method. Data were collected via observations and communication recordings during training flights with SAR crews and were amalgamated into a representative case study. The analysis demonstrates how the SAR team function within a distributed perceptual cycle whereby the actions of one team member become world information for another team member. Advancements to the EAST method are proposed and the implications of the research are discussed.

Practitioner Summary: This paper explores the perceptual cycle interactions of SAR crews using a novel EAST approach. The analysis demonstrates how the crew function as a distributed cognitive unit and applications in terms of training and design are discussed.     

Resource control for large-scale distributed simulation system over loosely coupled domains

Collaborative and distributed simulation environments that span across large interconnection networks, such as the Internet, are a promising way of supporting applications distributed over multiple computing sites. How-ever, communication-intensive distributed applications may suffer from variable communication delays, jitter, and latency experienced over the network. We term a loosely coupled domain the combination of multiple sites connected through an internetwork.In this paper, we focus on large-scale distributed simulations based upon local time warp deployed over several sites connected through an interconnection network (a loosely coupled domain). We propose and study a mechanism to tune elaboration according to varying communication performances, to reduce resource consumption and rollback costs that result from unpredictable network behavior. The mechanism is composed of two parts that operate in a completely distributed way: a local elaboration rate control and a message flow control. The experimental study is conducted through emulation to exert a control on injected delays. Our results show that the mechanism is able to globally tune the entire simulation, so as to reduce the escalation of allocated computational resources and the cost of rollbacks. As delays disappear, the mechanism allows elaboration to resume normal rate.     

Object-oriented data communication for loosely coupled control

The following discussion and examples are based on an object-oriented model for distributed and loosely coupled information systems. The model is used as a framework for a form-based application generator. Capabilities for loose coupling between workstations are illustrated with application examples.     

Parameter reduction schemes for loosely coupled HMMs

While Hidden Markov Models (HMMs) have been successful in many speech recognition tasks, performance on conversational speech is somewhat less successful, arguably due in part to the greater variation in timing of articulatory events. Loosely Coupled or Factorial HMMs (FHMMs) represent a family of models that have more flexibility for modeling such variation in speech, but there are tradeoffs to be studied in terms of computation and potential added confusability. This paper investigates two specific instances – Mixed-Memory and Parameter-Tied FHMMs – that can both be thought of as loosely coupled HMMs for modelling multiple time series. The Parameter-Tied FHMM, introduced here, has a potential advantage for speech modelling since it allows a left-to-right topology across the product state space. Experimental results on the ISOLET task show both models are feasible for speech recognition; TI-DIGITS recognition results show the Parameter-Tied FHMM is competitive with Multiband Models. State occupancy and pruning analyses show trends related to asynchrony that hold across the different models.     

DIVIDE: Distributed visual display of the execution of asynchronous, distributed algorithms on loosely coupled parallel processors

The issue of monitoring the execution of asynchronous, distributed algorithms on loosely coupled parallel processor systems is important for the purposes of (i) detecting inconsistencies and flaws in the algorithm; (ii) obtaining important performance parameters for the algorithm; and (iii) developing a conceptual understanding of the algorithm's behavior, for given input stimulus, through visualization. For a particular class of asynchronous distributed algorithms that may be characterized by independent and concurrent entities that execute asynchronously on multiple processors and interact with one another through explicit messages, information about the flow of messages and the activity of the processors may contribute significantly towards the conceptual understanding of the algorithm's behavior and the functional correctness of the implementation. The computation and subsequent display of important parameters, based upon the execution of the algorithm, is an important objective of DIVIDE. For instance, the mean and standard deviation values for the propagation delay of ATM cells between any two given Broadband-ISDN (BISDN) nodes in a simulation of BISDN network under stochastic input stimulus, as a function of time, are important clues to the degree of congestion in the Broadband-ISDN network. Although the execution of the algorithm typically generates high-resolution data, often, a coarse-level visual representation of the data may be useful in facilitating the conceptual understanding of the behavior of the algorithm. DIVIDE permits a user to specify a resolution less than that of the data from the execution of the algorithm, which is then utilized to coalesce the data appropriately. Given that this process requires significant computational power, for efficiency, DIVIDE distributes the overall task of visual display into a number of user-specified workstations that are configured as a loosely coupled parallel processor. DIVIDE has been implemented on a heterogeneous network of SUN Sparc 1+, Sparc 2, and 3/60 workstations, and performance measurements indicate significant improvement over that of a uniprocessor-based visual display.     

Cooperative distributed MPC of linear systems with coupled constraints

This paper develops a cooperative, distributed form of MPC for linear systems subject to persistent, bounded disturbances. The distributed control agents make decisions locally and communicate plans with each other. Cooperation is promoted by consideration of a greater portion of the system-wide objective by each local agent; specifically, a local agent designs hypothetical plans for other agents, sacrificing local performance for the benefit of system-wide performance. These hypothetical plans are never communicated and no negotiation takes place. The method guarantees robust feasibility by permitting only one agent to optimize per time step, while ‘freezing’ the plans of others, and sufficient conditions are given for robust stability. These properties hold for all structures of cooperation between agents. Thus, a key feature is that coupled constraint satisfaction is compatible with inter-agent cooperation.     

Scheduling and planning job execution of loosely coupled applications

Growth in availability of data collection devices has allowed individual researchers to gain access to large quantities of data that needs to be analyzed. As a result, many labs and departments have acquired considerable compute resources. However, effective and efficient utilization of those resources remains a barrier for the individual researchers because the distributed computing environments are difficult to understand and control. We introduce a methodology and a tool that automatically manipulates and understands job submission parameters to realize a range of job execution alternatives across a distributed compute infrastructure. Generated alternatives are presented to a user at the time of job submission in the form of tradeoffs mapped onto two conflicting objectives, namely job cost and runtime. Such presentation of job execution alternatives allows a user to immediately and quantitatively observe viable options regarding their job execution, and thus allows the user to interact with the environment at a true service level. Generated job execution alternatives have been tested through simulation and on real-world resources and, in both cases, the average accuracy of the runtime of the generated and perceived job alternatives is within 5%.     

Identification of coupled map lattice models of deterministic distributed parameter systems

This paper introduces a novel approach to the identification of Coupled Map Lattice (CML) models of linear and nonlinear infinite-dimensional systems from discrete observations. The method exploits the regularity of the CML model so that only a finite number of spatial measurements are required. The measurement system associated with a CML is discussed and some necessary conditions for the input/output equations to form a CML are presented. Numerical simulations illustrate the applicability of the proposed method.     

基于LQR的耦合动态互联系统分布式协作 负载均衡优化控制

针对一类非等同非线性耦合互联系统,提出分布式协作负载均衡优化控制方法.将子系统间的通信联系建模成有向图,借助输入输出反馈线性化技术,将耦合互联系统的分布式负载均衡控制设计问题转化为广义线性多智能体系统的同步跟踪问题;基于最近邻原则和LQR方法,设计增益可调的分布式协作负载均衡优化控制律,耦合强度依赖于通信拓扑,控制增益依赖于子系统模型;借助矩阵变换方法,整个闭环系统的渐近稳定性可以解耦成每个子系统的稳定性,在假定通信拓扑只含有生成树的条件下,借助李亚谱诺夫函数,可证明整个闭环系统是稳定的,且通过调节控制增益,可以得到期望的响应速度.仿真结果验证了所提出控制方法的有效性及可行性.     

Demand-driven logic simulation using a network of loosely coupled processors

Logic simulation is used extensively in the design of digital systems for the purpose of studying the behaviour of circuits under various conditions and for verifying the required performance of circuits. There is considerable interest in methods which reduce the simulation time during the design process. In this paper, we investigate how this can be achieved by simulating the action of logic circuits using a network of loosely coupled processors. Circuits modelled as directed graphs comprising clocked sequential components and (unclocked) arbitrary combinational logic gates can be partitioned into separate tasks each consisting of a sequential component with an associated network of combinational components. We present cost functions for evaluating a task subject to probabilistic assumptions about the functioning of the circuits. The circuit evaluation method used in the simulation process is significant. We apply lazy evaluation, a demand-driven evaluation strategy in which signals in the circuit are evaluated on a ‘need to do' basis, resulting in a considerable saving in circuit simulation time. We achieve distributed logic simulation using a network of workstations and show from experimental results that by using such a configuration, we essentially obtain a single computation engine which can be used to obtain speedups in circuit simulation when compared with uniprocessor simulation systems. Interprocess communications between tasks on different workstations proceed via remote procedure calls while local communications between tasks take place via shared memory. The method of partitioning used in the circuit model ensures that communications between tasks take place only at defined times in the simulation sequence.     

超级电容负载的耦合并联充电系统无源分布式协同控制

储能式轻轨车辆采用超级电容作为动力源,其并联充电系统每个充电机不可避免的存在着线路不对称、元器件老化及工艺误差等因素,使得输出电流不均衡.本文将并联充电系统的电流均衡问题抽象成一类非线性耦合动态互联系统的输出同步问题,结合系统的无源性,根据最近邻原则,借助饱和函数,设计了保证控制输入有界的输出同步控制器.利用子系统存储...     

A quasi-parallel method for the simulation of loosely coupled continuous subsystems

The concept of a quasi-parallel integration method is proposed as a potentially efficient way of handling the simulation of continuous systems that can be decomposed into a collection of loosely coupled sub-systems. Possible measures for evaluating the computational advantage of such an approach are formulated and then used to identify characteristics of the given system that would assure substantial gains if the method were applied. A particular implementation of such a quasi-parallel method is described and the results of a series of numerical experiments are given. These provide some insight into the question of trade-offs between accuracy and computational gain.     

Using cognitive artifacts to understand distributed cognition

Studies of patient safety have identified gaps in current work including the need for research about communication and information sharing among healthcare providers. They have also encouraged the use of decision support tools to improve human performance. Distributed cognition is the shared awareness of goals, plans, and details that no single individual grasps. Cognitive artifacts are objects such as: schedules, display boards, lists, and worksheets that form part of a distributed cognition. Cognitive artifacts that are related to operating room (OR) scheduling include: the availabilities sheet, master schedule, OR graph, and OR board. All provide a "way in" to understand how teams in the acute care setting dynamically plan and manage the balance between demand for care and the resources available to provide it. This work has import for the way that information technology supports the organization, management, and use of healthcare resources. Better computer-supported cognitive artifacts will benefit patient safety by making teamwork processes, planning, communications, and resource management more resilient.     

Design and analysis of a fifo linked loosely coupled dual processor system

This paper describes the design, implementation and performance analysis of a loosely coupled dual processor system employing FIFO based communication links. Two cards, each supporting a FIFO queue with 8-bit static RAMs and associated counters, are used to connect two IBM PCs. The circuit is controlled entirely by an Altera EP900 which facilitates possible modifications of hardware in the future. Overflow and conflict error conditions trigger and interrupt request and provisions have been made to retry the last operation upon the occurrence of such error conditions. Details on the software developed for interprocessor communication have been provided. The performance of the dual processor system has been analysed with matrix multiplication operations and it is found that when compared to a single processor system, the dual processor system offers a higher throughput when the order of the matrices is seven or above. The system is currently being used as an aid for teaching various concepts on parallel programming and design aspects for developing hardware for multiprocessor systems and subsystems.     

Early parallelism with a loosely coupled array of processors: The ICAP experiment

The hardware, system software and Scientific application examples with relative performances are reported for the ICAP-1, ICAP-2, ICAP-3 and ICAP-3090 experimental systems, with emphases on motivation, strategy and accomplishments. These pioneering efforts are considered in the light of future large-scale computational applications, which will require parallel super computing power and also a new outlook to computational models.     

Dynamic distributed systems

This paper introduces a new methodology for building flexible and programmable multiprocessor systems. It is based on a distributed implementation of monitors which is supported by a system-wide address relocation mechanism. This provides the dynamic reallocation of processes and monitors within the system. Methods of implementing the communications subsystem based on a number of common network architectures are presented. An algorithm which effects dynamic resource allocation is presented. Its effect is that groups of processes which are interacting through a monitor will tend to accumulate at various sites in the system in a manner reflecting the dynamic interaction patterns of the program. This is accomplished without there being any centralized control, or even knowledge of the overall program interactions. The feasibility of the system has been investigated using a model system running on a loosely connected dual processor system.     

Weighted fair share scheduling for loosely controlled concurrent event systems

In asynchronous event systems, the production of an event is decoupled from its consumption via an event queue. The loose coupling of such systems allows great flexibility as to where and when within the system the event handler of a given event is actually executed, allowing them to scale with increasing number of processors on a given node or across multiple nodes in a distributed system. Although this flexibility is useful in heterogeneous distributed systems, such as SOA, it may appear not to be well suited for real-time systems, which require an upper bound on how long an event can remain unhandled in a queue. However, we show how the weighted fair scheduling algorithms developed for QoS (quality of service) routing can be adapted to event queues to bound the delay between production and consumption. We achieve this, despite the fact that the underlying execution environment is only weakly controlled, through the use of predictive techniques on a calibrated model of the event system. Our choice of algorithms and data structures is driven in part by the highly concurrent nature of the system. We show how a weighted fair scheduler can be built on a lock-free concurrent priority queue. We analyze the performance of various such queues proposed in the literature and show that a very simple linear quantizing queue yields the best performance.     

Deadlock detection in distributed systems

The author describes a series of deadlock detection techniques based on centralized, hierarchical, and distributed control organizations. The point of view is that of practical implications. An up-to-date and comprehensive survey of deadlock detection algorithms is presented, their merits and drawbacks are discussed, and their performances (delays as well as message complexity) are compared. Related issues such as correctness of the algorithms, performance of the algorithms, and deadlock resolution, which require further research are examined