A process partitioning technique for constructing decentralized web service compositions

Web service compositions have been widely applied in different applications. A service composition is usually implemented in either a centralized or decentralized manner. Compared with the centralized service composition, the decentralized composition has no central control component, and components interact with each other directly, thereby achieving better performance. Process partitioning is a technique to divide a process into multiple parts and has been shown that it can be successfully applied to decentralizing process-driven service compositions. This paper proposes a new process partitioning technique for constructing decentralized service compositions. The proposed technique, which is based on typed digraphs and a graph transformation technique, is used for exploring available process partitioning solutions. For applications, this paper discusses the topology and interaction features about the partitioning solutions and summarizes a ranking method for them. Three experiments are conducted to evaluate the proposed methods in this paper. Experimental results show that the proposed methods can be applied in constructing decentralized service compositions effectively. In addition, the results also show that the decentralized compositions can have lower average response times and higher throughputs than the corresponding centralized compositions in the experiments.     

A self-organizing flock of Condors

Condor enables high throughput computing using off-the-shelf cost-effective components. It also supports flocking, a mechanism for sharing resources among Condor pools. Since Condor pools distributed over a wide area can have dynamically changing availability and sharing preferences, the current flocking mechanism based on static configurations can limit the potential of sharing resources across Condor pools. This paper presents a technique for resource discovery in distributed Condor pools using peer-to-peer mechanisms that are self-organizing, fault-tolerant, scalable, and locality-aware. Locality-awareness guarantees that applications are not shipped across long distances when nearby resources are available. Measurements using a synthetic job trace show that self-organized flocking reduces the maximum job wait time in queue for a heavily loaded pool by a factor of 10 compared to without flocking. Simulations of 1000 Condor pools are also presented and the results confirm that our technique discovers and utilizes nearby resources in the physical network.     

Towards role-based administration in network information services

Client-server networks have grown tremendously since the mid-1980s. The information they store changes much more rapidly than it did during the time at beginning. The size and complexity of these networks required new, autonomous administration practices. Network Information Services was designed to address these requirements. As one of the network information services, NIS+ is a widely used network protocol. It allows networked machines to have a common interface regardless of the workstation that a user logs into. NIS+ keeps all information into tables to support a common interface between networked machines. In the most of case these information are controlled by centralized manner. Centralized management of NIS+ tables in large systems is a tedious and costly task. An appealing possibility is to use role and role hierarchy to facilitate decentralized administration of NIS+ tables which has not been previously recognized in the literature. This paper presents decentralized administration of NIS+ tables using the notion of role and also shows how to simulate role hierarchy in NIS+ groups.     

Analytic models of adaptive load sharing schemes in distributedreal-time systems

In a distributed real-time system, nonuniform task arrivals may temporarily overload some nodes while leaving some other nodes idle. As a result, some of the tasks on an overloaded node may miss their deadlines even if the overall system has the capacity to meet the deadlines of all tasks. A decentralized, dynamic load sharing (LS) scheme has been proposed as a solution to this problem. Analytic queuing models to comparatively evaluate this LS scheme as well as three other schemes-no LS, LS with random selection of a receiver node, and LS with perfect information- are developed. The evolution of a node's load state is modeled as a continuous-time semi-Markov process, where cumulative execution time (CET), rather than the commonly-used queue length (QL), is employed to describe the workload of a node. The proposed scheme is compared against other LS schemes. The validity of analytic models is checked with simulations. Both analytic and simulation results indicate that by using judicious exchange/use of state information and Bayesian decision mechanism, the proposed scheme makes a significant improvement over other existing LS schemes in minimizing the probability of dynamic failure     

GS—ZDDS中的自定义特征

在自主开发的二维参数化绘图软件中,提出了一种用于与用户专业设计程序相集成的自定义特征的概念,实现了设计计算过程的信息共享和局部并行,提高了设计效率,体现了设计构件重用的思想,并且大大减小了用户专用的设计系统开发的工作量,系统具有良好的可扩展性。     

Modeling and control of workstation level information flow in FMS using modified Petri nets

A flexible manufacturing system (FMS) has a traditional structure of three levels: cell, workstation, and equipment. The workstation level plays an important role in the overall performance of the FMS. This paper focuses on modeling and control of the FMS workstation level information flow. In order to have a unified workstation level system structure, front-end interfaces are introduced as a standard communication medium between the workstation level and the equipment level. A detailed information flow analysis is then carried out on the workstation level. For modeling purposes, a modified Petri net is proposed with its increased modeling capability over an ordinary Petri net. It associates data structures with places and programs with transitions. Finally, the modified Petri net is used to model and control the FMS workstation level information flow. The designed control system has been implemented in a real manufacturing factory with satisfactory performance.     

基于风险策略的多单元连续双向拍卖的网格资源分配

针对计算网格资源的特点,提出一种基于风险策略的多单元连续双向拍卖的网格资源分配机制,实现对网格资源灵活有效的管理。首先,介绍了基于多单元连续双拍卖的网格资源分配框架。其次,针对计算网格资源的有限性,提出了RB2-MCDA机制。RB2-MCDA机制是在多单元连续双向拍卖中,代理采用Risk-Based2策略进行资源交易。Risk-Based2策略是一种基于风险行为的代理策略。实验结果表明,在不同规模的有限资源的计算网格中采用RB2-MCDA机制能够实现较高的资源分配效率,当资源需求量接近供给量时,分配效率超过99%。     

Building access control policy model for privacy preserving and testing policy conflicting problems

This paper proposes a purpose-based access control model in distributed computing environment for privacy preserving policies and mechanisms, and describes algorithms for policy conflicting problems. The mechanism enforces access policy to data containing personally identifiable information. The key component is purpose involved access control models for expressing highly complex privacy-related policies with various features. A policy refers to an access right that a subject can have on an object, based on attribute predicates, obligation actions, and system conditions. Policy conflicting problems may arise when new access policies are generated that are possible to be conflicted to existing policies. As a result of the policy conflicts, private information cannot be well protected. The structure of purpose involved access control policy is studied, and efficient conflict-checking algorithms are developed and implemented. Finally a discussion of our work in comparison with other related work such as EPAL is presented.     

Enhancing decentralized service discovery in open service-oriented multi-agent systems

Service-oriented multi-agent systems are dynamic systems that are populated by heterogeneous agents. These agents model their functionality as services in order to allow heterogeneous agents or other entities to interact with each other in a standardized way. Furthermore, due to the large-scale and adaptative needs of the system, traditional directory facilitators or middle-agents are not suitable for the management of agent services. This article proposes the introduction of homophily in service-oriented multi-agent systems to create efficient decentralized and self-organized structures where agents have a greater probability of establishing links with similar agents than with dissimilar ones. This similarity is based on two social dimensions: the set of services that an agent provides and the organizational roles that it plays. A second contribution is an algorithm for service discovery that it is carried out taking into account the local information that is related to the homophily between agents. The experiments compare our proposal with other proposals in distributed environments. The results show that the proposed structure and algorithm offer desirable features for service discovery in decentralized environments. Specifically, these features provide short paths and a high success rate in the service discovery process and resilience under deliberate failures.     

An information-leak analysis system based on program slicing

For programs using secret information such as credit card numbers, preventing information-leaks is important. Denning, for example, has proposed a mechanism to certify that a given program does not violate a security policy. Kuninobu, on the other hand, has proposed a more practical framework for calculating the secrecy level of each output value from the secrecy level set to each input value, but no implementation has been yet explored. In this paper, we propose an implementation method for information-leak analysis, and show a system we have implemented based on program slicing. We have applied this system to a credit card program. Our results show that information-leak analysis before practical use of the program is important.     

大工业过程的稳态模型分散辨识及其强一致性分析

针对动态线性大工业过程,提出了获得其可分稳态模型强一致性估计的分散辨识方法.该方法仅使用设定点的阶跃信号作为输入激励信号,并且每个子过程的输入输出稳态模型辨识是在相应的局部单元完成的,因而大大减少了对过程的干扰和信息的交换量.所提出的方法简洁,并且辨识精度高,仿真结果说明了该辨识方法的有效性和实用性.     

基于信息混淆的社会网络隐私保护机制

提出了一种基于信息混淆的社会网络隐私保护机制,其原理在于对整个社会网络里的隐私信息进行混淆,而非加密,使得需要保护的隐私信息以环形结构在社会网络里扩散开来。该机制以非集中化的方式工作,由用户之间的相互协作来保护用户的隐私信息。以"人人网"为平台,利用Firefox的扩展开发功能实现了该隐私保护的核心机制,证明了其可行性与可用性。该机制能够保证多方面的利益:要求隐私保护的主体用户、广告商、经过授权的用户及第三方应用。     

Gene selection with guided regularized random forest

The regularized random forest (RRF) was recently proposed for feature selection by building only one ensemble. In RRF the features are evaluated on a part of the training data at each tree node. We derive an upper bound for the number of distinct Gini information gain values in a node, and show that many features can share the same information gain at a node with a small number of instances and a large number of features. Therefore, in a node with a small number of instances, RRF is likely to select a feature not strongly relevant.Here an enhanced RRF, referred to as the guided RRF (GRRF), is proposed. In GRRF, the importance scores from an ordinary random forest (RF) are used to guide the feature selection process in RRF. Experiments on 10 gene data sets show that the accuracy performance of GRRF is, in general, more robust than RRF when their parameters change. GRRF is computationally efficient, can select compact feature subsets, and has competitive accuracy performance, compared to RRF, varSelRF and LASSO logistic regression (with evaluations from an RF classifier). Also, RF applied to the features selected by RRF with the minimal regularization outperforms RF applied to all the features for most of the data sets considered here. Therefore, if accuracy is considered more important than the size of the feature subset, RRF with the minimal regularization may be considered. We use the accuracy performance of RF, a strong classifier, to evaluate feature selection methods, and illustrate that weak classifiers are less capable of capturing the information contained in a feature subset. Both RRF and GRRF were implemented in the “RRF” R package available at CRAN, the official R package archive.     

Reinforcement learning-based dynamic obstacle avoidance and integration of path planning

Deep reinforcement learning has the advantage of being able to encode fairly complex behaviors by collecting and learning empirical information. In the current study, we have proposed a framework for reinforcement learning in decentralized collision avoidance where each agent independently makes its decision without communication with others. In an environment exposed to various kinds of dynamic obstacles with irregular movements, mobile robot agents could learn how to avoid obstacles and reach a target point efficiently. Moreover, a path planner was integrated with the reinforcement learning-based obstacle avoidance to solve the problem of not finding a path in a specific situation, thereby imposing path efficiency. The robots were trained about the policy of obstacle avoidance in environments where dynamic characteristics were considered with soft actor critic algorithm. The trained policy was implemented in the robot operating system (ROS), tested in virtual and real environments for the differential drive wheel robot to prove the effectiveness of the proposed method. Videos are available at https://youtu.be/xxzoh1XbAl0.

     

Design and evaluation of effective load sharing in distributedreal-time systems

In a distributed real-time system, uneven task arrivals temporarily overload some nodes and leave others idle or underloaded. Consequently, some tasks may miss their deadlines even if the overall system has the capacity to meet the deadlines of all tasks. An effective load-sharing (LS) scheme is proposed as a solution to this problem. Upon arrival of a task at a node, the node determines whether the node can complete the task in time under the minimum-laxity first-served policy. If the task cannot be guaranteed, or if guarantees of some other tasks are to be violated as a result of the addition of this task to the existing schedule, the node looks up the list of loss-minimizing decisions and determines the best node among a set of nodes in its physical proximity, called its buddy set, to which the task(s) may be transferred. This list of decisions is periodically updated using Bayesian decision analysis and prior/posterior state distributions. These probability distributions are derived from the information collected via time-stamped state-region change broadcasts within each buddy set. By characterizing the inconsistency between a node's “observed” state and the corresponding true state with prior and posterior distributions, the node can first estimate the states of other nodes, and then use them to reduce the probability of transferring a task to an “incapable”) node. Moreover, the use of prior and posterior distributions and Bayesian analysis has made the proposed scheme robust to the variation of design parameters that usually require fine-tuning for adaptive LS. The performance of the proposed scheme is evaluated via simulation, along with five other schemes: no LS, LS with state probing, LS with random selection, LS with focused addressing, and perfect LS     

基于Linux集群的socket迁移技术

以MOSIX，Condor等为代表的负载均衡集群实现了进程迁移技术。但是目前这项技术中由于没有实现对套接字这一重要的资源的迁移支持，大大限制了它的应用范围，特别是对于网络应用程序的迁移。MOSIX是通过其固有的deputy／remote机制实现间接的支持，而Condor根本就不支持网络程序的迁移。文中讨论了Linux集群中的socket迁移问题，然后分析了一种基于CRAK集群系统的套接字迁移系统MIGSOCK的实现机制及未解决的问题，MIGSOCK通过增加一个Linux Module和少量修改TCP层的方式，在Linux负载均衡集群中实现了内核级可迁移socket，为解决这一问题提供了一种实际的可参考的解决方案。     

Maintenance scheduling incorporating dynamics of production system and real-time information from workstations

In this paper, a new approach to maintenance scheduling for a multi-component production system which takes into account the real-time information from workstations including remaining reliability of equipments as well as work-in-process inventories in each workstation is proposed. To model dynamics of the system, other information like production line configuration, cycle times, buffers’ capacity and mean time to repair of machines are also considered. Using factorial experiment design the problem is formulated to comprehensively monitor the effects of each possible schedule on throughput of the production system. The optimal maintenance schedule is searched by genetic algorithm-based optimization engine implemented in a simulation optimization platform. The proposed approach exploits all of makespans of planning horizon to find the best opportunity to perform maintenance actions on degrading machines in a way that maximizes the system throughput and mitigates the production losses caused by imperfect traditional maintenance strategies. Finally the proposed method is tested in a real production line to magnify the accuracy of proposed scheduling method. The experimental results indicate that the proposed approach guarantees the operational productivity and scheduling efficiency as well.     

A concept for decentralization: Production management — Workstations and their tools

The necessity of more flexibility and shorter response times requires new information tools for running decentralized PM-systems. With the help of personal computers, specifically designed PM-workstations can support this decentralization. In contrast to rather inflexible and sometimes overloaded centralized software such PM-workstations are providing an object-oriented user interface and are specifically designed to the respective functions of the user. Offering the user graphics and window-techniques, these workstations are supporting the user's acting instead of the common passive reacting. A PM-workstation is implemented by layers of tools. It can be used within the PM-information system autonomically, as an intelligent terminal as well as an “agent” in a distributed information system. A special realization of an assembly management workstation is demonstrated.     

Query optimization in information integration

The problem of decentralized data sharing, which is relevant to a wide range of applications, is still a source of major theoretical and practical challenges, in spite of many years of sustained research. In this paper we focus on the challenge of efficiency of query evaluation in information integration systems that use the global-as-view approach, with the objective of developing query-processing strategies that would be widely applicable and easy to implement in real-life applications. Our algorithms take into account important features of today’s data sharing applications: XML as likely interface or representation for data sources; the potential for information overlap across data sources; and the need for inter-source processing, as in joins of data across sources. The focus of this paper is on performance-related characteristics of several alternative approaches that we propose for efficient query processing in information integration, including an approach that uses materialized restructured views. We use synthetic and real-life datasets in our implementation of an information integration system shell to provide experimental results that demonstrate that our algorithms are efficient and competitive in the information integration setting. In addition, our experimental results allow us to make context-specific recommendations on selecting query-processing approaches from our proposed alternatives. As such, our approaches could form a basis for scalable query processing in information integration and interoperability in many practical settings.     

PBS作业管理系统分析

本文对PBS作业管理系统进行了分析.通过与Condor系统的比较,介绍了PBS系统的功能和特性;讨论了PBS的作业调度策略;分析了PBS系统下作业执行过程;通过设计和运行一个作业的实例,对PBS作业管理系统进行了进一步的分析.