Timers for Distributed Systems

We deal with temporal aspects of distributed systems, introducing and studying a new model called timed distributed π-calculus. This model extends distributed π-calculus with timers, transforming the communication channels into temporary resources. Distributed π-calculus describes located interactions between processes with restricted access to resources. We introduce time constraints by considering timeout timers for channels. Combining these timers with types and locations, we provide a formal framework able to describe complex systems with constraints on time and on resource access. Its typing system and operational semantics are presented. It is proved that the passage of time does not interfere with the typing system. The new model is proved to be sound by using a method based on subject reduction.     

安全群组通讯在流媒体传输方面的应用

随着网络的快速发展，基于组的通讯已经成为一种重要的通讯机制，它可提供可靠的、顺序的消息传送以及提供组成员关系服务。安全群组通讯系统(SGCS)构建于群组通讯系统之上，为成员间传输的消息提供安全保证。安全群组通讯可应用于许多领域，文中阐述其系统结构、工作原理，介绍如何将其应用在流媒体传输方面，在通讯过程中传输音频流和视频流，从而实现一个安全多媒体会议的原型系统。实验结果表明，该原型系统在局域网或宽带网实验环境中运行稳定，音频流和视频流均非常流畅；在拨号广域网中设置较低的会话质量同样可以达到安全多媒体会议的通讯效果。     

SIP协议在Java消息服务系统中的应用研究

会话发起协议(session initiation protocol, SIP)作为一种新兴的因特网多媒体通讯协议,在建立多方多媒体通讯和IP多媒体子系统等方面有着很大的优越性,同时作为NGN中的重要协议,SIP协议也越来越受到业界的关注.Java为SIP应用系统开发提供了强大的JAIN(Java API for integrated networks)-SIP开发平台,用于构建复杂的分布式SIP应用系统.对SIP消息结构和通信过程进行了初步研究,并结合实际项目阐述了如何使用SIP Servlet来建立基于SIP的消息服务系统.     

An Operational Semantics for Shared Messaging Communication

Shared Messaging Communication (SMC) has been introduced in [Satya Kiran M.N.V., Jayram M.N., Pradeep Rao, and S.K. Nandy. A complexity effective communication model for behavioral modeling of signal processing applications. In Proceedings of 40th Design Automation Conference, 2003] as a model of communication which reduces communication costs (both in terms of communication latency and memory usage) by allowing tasks to communicate data through special shared memory regions. Sending a reference to an otherwise inaccessible memory regions rather than the data itself, the model combines the advantages of message passing and shared memories. Experimental results have shown that SMC in case of large data payloads clearly outperforms the classical message passing.In this paper we give a formal operational semantics to SMC exhibiting unambiguously the effect of executing an SMC command on local and shared memories. Based on this semantics we show that any program using message passing can be proved to be weakly bisimilar to one based on SMC and that with respect to communication costs the latter is amortised cheaper, [A. Kiehn and S. Arun-Kumar. Amortised bisimulations. In Proceedings of FORTE 2005, number 3731 in Lecture Notes in Computer Science, pages 320–334. Springer-Verlag, 2005].     

A family of optimal termination detection algorithms

An important problem in distributed systems is to detect termination of a distributed computation. A computation is said to have terminated when all processes have become passive and all channels have become empty. In this paper, we present a suite of algorithms for detecting termination of a non-diffusing computation for an arbitrary communication topology under a variety of conditions. All our termination detection algorithms have optimal message complexity. Furthermore, they have optimal detection latency when message processing time is ignored. A preliminary version of the paper first appeared in the 18th Symposium on Distributed Computing (DISC), 2004 [27].     

A parallel and distributed meta-heuristic framework based on partially ordered knowledge sharing

We propose a new distributed and parallel meta-heuristic framework to address the issues of scalability and robustness in the optimization problem. The proposed framework, named PADO (Parallel And Distributed Optimization framework), can utilize heterogeneous computing and communication resources to achieve scalable speedup while maintaining high solution quality. Specifically, we combine an existing meta-heuristic framework with a loosely coupled distributed island model for scalable parallelization. Based on a mature sequential optimization framework, we implement a population-based meta-heuristic algorithm with an island model for parallelization. The coordination overhead of previous approaches is significantly reduced by using a partially ordered knowledge sharing (POKS) model as an underlying model for distributed computing. The resulting framework can encompass many meta-heuristic algorithms and can solve a wide variety of problems with minimal configuration. We demonstrate the applicability and the performance of the framework with a traveling salesman problem (TSP), multi-objective design space exploration (DSE) problem of an embedded multimedia system, and a drug scheduling problem of cancer chemotherapy.     

Implementation of hierarchical F-channels for high-performance distributed computing

Summary High performance distributed computing systems require high performance communication systems.F-channels andHierarchical F-channels address this need by permitting a high level of concurrency like non-FIFO channels while retaining the simplicity of FIFO channels critical to the design and proof of many distributed algorithms. In this paper, we present counter-based implementations for F-channels and Hierarchical F-channels using message augmentation-appending control information to a message. These implementations guarantee that no messages are unnecessarily delayed at the receiving end. Keith Shafer received the B.A. degree in computer science and mathematics in 1986 from Mount Vernon Nazarene College, Mount Vernon, Ohio, USA, and the M.S. and Ph.D. degrees in computer science from The Ohio State University, Columbus, Ohio, USA, in 1988 and 1992, respectively. He is currently a Senior Research Scientist at OCLC Online Computer Library Center Inco, Dublin, OH, USA. His research interests include tools for comparing logical channels and methods for automatically constructing corpus grammars from tagged documents as an aid for database preparation and document conversion. Dr. Shafer is a member of the IEEE Computer Society. Mohan Ahuja received the M.A. degree in 1983 and the Ph.D. degree in 1985, both in computer science, from the University of Texas at Austin. He is currently with Department of Computer Science and Engineering, Univ. of California, San Diego. His recent research contributions include Global Flushing, message receipt in Receive-Phases, Incremental Publication of a Partial Order, Design of Highways (a high-performance distributed programming system) and — in collaboration with others — Passive-space and Time View, Performance evaluation of F-Channels, and Units of Computation in Fault-Tolerant Distributed Systems. His current research interests are in high-performance distributed communication and computing architectures, building high-performance systems, distributed operating systems, distributed algorithms, fault tolerance, and performance evaluation.Parts of this paper appeared in two conference papers, (1) Distributed Modeling and Implementation of High Performance Communication Architectures, in proceedings of the Thirteenth IEEE International Conference on Distributed Computing Systems, papes 56–65, 1993 and (2) Process-Channel_agem-Process model of asynchronous distributed communication, in proceedings of the Twelfth IEEE International Conference on Distributed Computing Systems, pages 4–11, 1992     

分布式并行数据库中基于调度的多线程通信模型之研究

分布式并行数据库系统以其高性能倍受关注，高效合理的内部通信系统是分布式并行数据库系统极其关键的组成部分、为此，在分析现有多种通信模型的基础上，建立了一种基于调度的多线程通信模型，该通信模型采用多个线程收发数据，并根据节点运行情况动态调度接收线程和发送线程，既保证了内部通信的通信性能，又不会使系统的时外处理能力成为新的瓶颈．该模型已被成功应用于成都市电子政务的系统平台——分布式并行数据库系统DPSQL。     

基于消息语义解析的软件网络行为分析

通过对软件网络行为的研究,提出了通过结合动态分析软件行为技术和网络消息语义解析技术对软件网络行为进行分析的系统模型。系统主要由动态二进制分析模块、消息语义解析模块和网络行为分析模块组成。通过动态二进制分析,利用行为监控和劫持机制,获取软件对于应用程序编程接口(API)函数和系统函数的调用情况;通过动态污点分析,对消息语义进行解析。实验验证表明,软件行为和消息语义解析的结合可以用于分析软件网络行为。     

Distributed Tip Decomposition on Large Bipartite Graphs

Tip decomposition has a pivotal role in mining cohesive subgraphs in bipartite graphs. It is a popular research topic with wide applications in document clustering, spam group detection, and analysis of affiliation networks. With the explosive growth of the bipartite graph data scale in these scenarios, it is necessary to use distributed methods to realize its effective storage. For this reason, this paper studies the problem of the tip decomposition on a bipartite graph in the distributed environment for the first time. Firstly, a new relay-based communication mode is proposed to realize effective message transmission when the given bipartite graph is decomposed in a distributed environment. Secondly, the Distributed Butterfly Counting (DBC) algorithm and the Distributed Tip Decomposition (DTD) algorithm are designed. In particular, a controllable parallel vertex activation strategy is proposed to solve the problem of memory overflow when DBC decomposes large-scale bipartite graphs. Finally, the message pruning strategy based on vertex priority and message validity pruning strategy are introduced to further improve the efficiency of the algorithm by reducing redundant communication and computing overhead. The experiment is deployed on the high-performance distributed computing platform of the National Supercomputing Center. The effectiveness and efficiency of the proposed algorithms are verified by experiments on several real datasets.     

分布式多媒体网络协作平台的研究

计算机支持的协同工作(CSCW)体现并符合信息时代人们工作的分布性、交互性和协同性的特征,涉及分布式系统、计算机通信、人机交互、人工智能和社会科学等诸多方面,因而日益受到人们的重视。文章结合CSCW技术提出了一个通用分布式多媒体网络协作平台的体系结构,分析了多媒体通信,用户协作信息管理,协同应用的并发控制机制等问题,最终实现了分布式、网络传输、多媒体技术在平台中的集成,并介绍了几个应用实例。     

Distributed Model Checking: From Abstract Algorithms to Concrete Implementations

Distributed Model Checking (DMC) is based on several distributed algorithms, which are often complex and error prone. In this paper, we consider one fundamental aspect of DMC design: message passing communication, the implementation of which presents hidden tradeoffs often dismissed in DMC related literature. We show that, due to such communication models, high level abstract DMC algorithms might face implicit pitfalls when implemented concretely. We illustrate our discussion with a generic distributed state space generation algorithm.     

具有迁移能力的基于Agent分布仿真中的通信系统

对基于Agent系统的分布仿真是仿真领域的重要研究和应用方向，而分布仿真中的通信系统是其中的基础部分．提出并实现了一种支持基于Agent系统分布仿真的通信系统．该系统除了提供基本的仿真通信支持外，还能够有效地支持仿真中Agent的迁移，具有对应用系统透明、通信效率高等优点．首先给出了通信系统的结构及其基本思想，对局部服务Agent和通信过程进行了详细的描述；从应用系统级和分布仿真级两个层次，给出了结构化的通信协议；在此基础之上，给出了完整的Agent迁移支持方案，包括迁移过程、迁移过程中的消息处理和迁移后的通信；最后对通信系统的性能进行了测试．     

分布式多媒体系统的关键问题探讨与研究

依据多媒体时间模型和同步模型,面向对象的并发系统和分布式系统的研究已经取得不少结果。但由于特殊的要求,这些结果已不能满足实际应用的需要,为此,我们就分布式多媒体系统中的同步这一关键问题进行了研究。本文首先论述了形式化规范语言LOTOS的基本概念与约定,对其进行了基于时间的改进和扩充,引入了离散时间域和时间操作算子,然后确定其相应的语法定义和语义规则,通过仔细分析分布式环境下的多媒体同步问题,基于时间扩充的LOTOS,给出了一种特殊的多媒体同步系统以及具体的算法描述,通过实例对分布环境下多媒体信息同步问题在实际中的应用进行了深入的探讨。     

分布式智能视觉系统中基于KQML的Agent通信模型

分布式智能视觉系统中多个Visual Agent之间的通信采用KQML实现，但仅凭KQML预留的行为原语是无法实现这种Agent闻任务级的高级、复杂交互的．因此，对KQML扩充了7条行为原语，并给出了定义、语义，构建了分布式智能视觉系统的Agent通信模型．     

建立分布式多媒体系统的体系结构参考模型

分布式多媒体系统具有广阔的应用前景。但由于缺乏一致的体系结构，其研究和开发均受到了很大的限制。本文首先给出分布式多媒体系统的资源配置模型和一般功能需求，引入虚拟设备、虚拟连接、ＱｏＳ等概念，最后描述了我们所使用的分布式多媒体系统体系结构参考模型。该模型对理解分布式多媒体系统的特点和工作原理亦有相当帮助。     

Traffic distribution for end-to-end QoS routing with multicast multichannel services

With the development of multimedia group applications and multicasting demands, the construction of multicast routing tree satisfying Quality of Service (QoS) is more important. A multicast tree, which is constructed by existing multicast algorithms, suffers three major weaknesses: (1) it cannot be constructed by multichannel routing, transmitting a message using all available links, thus the data traffic cannot be preferably distributed; (2) it does not formulate duplication capacity; consequently, duplication capacity in each node cannot be optimally distributed; (3) it cannot change the number of links and nodes used optimally. In fact, it cannot employ and cover unused backup multichannel paths optimally. To overcome these weaknesses, this paper presents a polynomial time algorithm for distributed optimal multicast routing and Quality of Service (QoS) guarantees in networks with multichannel paths which is called Distributed Optimal Multicast Multichannel Routing Algorithm (DOMMR). The aim of this algorithm is: (1) to minimize End-to-End delay across the multichannel paths, (2) to minimize consumption of bandwidth by using all available links, and (3) to maximize data rate by formulating network resources. DOMMR is based on the Linear Programming Formulation (LPF) and presents an iterative optimal solution to obtain the best distributed routes for traffic demands between all edge nodes. Computational experiments and numerical simulation results will show that the proposed algorithm is more efficient than the existing methods. The simulation results are obtained by applying network simulation tools such as QSB, OpNet and MATLB to some samples of network. We then introduce a generalized problem, called the delay-constrained multicast multichannel routing problem, and show that this generalized problem can be solved in polynomial time.     

Network access protocol for hard real-time communication systems

Distributed hard real-time systems are characterized by communication messages associated with timing constraints, typically in the form of deadlines. A message should be received at the destination before its deadline expires. Carrier sense multiple access with collision detection (CSMA/CD) appears to be one of the most common communication network access schemes that can be used in distributed hard real-time systems. In this paper, we propose a new real-time network access protocol which is based on the CSMA/CD scheme. The protocol classifies the messages into two classes as ‘critical’ and ‘noncritical’ messages. The messages close to their deadlines are considered to be critical. A critical message is given the right to access the network by preempting a noncritical message in transmission. Extensive simulation experiments have been conducted to evaluate the performance of the protocol. It is shown that the protocol can provide considerable improvement over the virtual time CSMA/CD protocol proposed for hard real-time communication by Zhao et al.¹.     

多媒体会议系统研究

多媒体会议系统是一种典型实用的计算机支持的协同工作（ＣＳＣＷ）应用，最近几年发展很快，受到了广泛的重视。我们从多媒体技术和计算机网络技术两方面出发对多媒体会议系统进行系统研究，在此基础上，提出多媒体会议系统的总体设计，特别是针对多媒体会议系统的关键问题和支持多媒体网络协议存在的问题，提出了多媒体通信服务模型，以试衅弥补当前网络协议对服务质量（ＱＯＳ）的不足，同时也给出了新服务模型下的参考实现框架。     

分布式多媒体同步事务规划

文章针对分布式多媒体应用所含的复杂时态关系和分布性特性,利用同步代理构建了一个基于代理的分布式多媒体同步规划系统。并通过对传统Ｐｅｔｒｉ网的扩展,对分布式同步Ｐｅｔｒｉ网（ＤＳＰＮ）进行了定义,并利用ＤＳＰＮ对同步代理进行建模。最后通过对多媒体应用实例的分析,简要说明系统的操作流程。