Some data mining tasks can produce such great amounts of data that we have to cope with a new knowledge management problem. Frequent itemset mining fits in this category. Different approaches were proposed to handle o...
详细信息
Partial-order data structures used in distributed-system observation tools typically use vector timestamps to efficiently determine event precedence. Unfortunately all current dynamic vector-timestamp algorithms eithe...
详细信息
ISBN:
(纸本)0769510779
Partial-order data structures used in distributed-system observation tools typically use vector timestamps to efficiently determine event precedence. Unfortunately all current dynamic vector-timestamp algorithms either require a vector of size equal to the number of processes in the computation or require a graph search operation to determine event precedence. This fundamentally limits the scalability of such observation systems. In this paper we present an algorithm for hierarchical, clustered vector time-stamps. We present results for a variety of computation environments that demonstrate such timestamps can reduce space consumption by more than an order-of-magnitude over Fidge/Mattern timestamps while still providing acceptable time bounds for computing timestamps and determining event precedence.
In the biotechnology field, the deployment of the Multiple Sequence Alignment (MSA) problem, which is a high performance computing demanding process, is one of the new challenges to address on the new parallelsystems...
详细信息
This paper describes an architecture that provides support for quality of service (QoS) in open systems. The Quartz QoS architecture aims to avoid the dependency on specific platforms that limits the application of mo...
详细信息
This paper describes an architecture that provides support for quality of service (QoS) in open systems. The Quartz QoS architecture aims to avoid the dependency on specific platforms that limits the application of most existing QoS architectures in open, heterogeneous and distributedsystems. Quartz adopts a flexible and extensible platform-independent design that allows its internal components to be rearranged dynamically, adapting the architecture to the surrounding environment in order to accommodate the differences among diverse computing platforms. Further significant problems found in other QoS architectures, such as the lack of transparency, flexibility and expressiveness in the specification of QoS requirements and limited support for resource adaptation, are also addressed by quartz. This paper compares Quartz to other QoS architectures found in the literature, presents a prototype implementation of Quartz, and shows how Quartz is integrated with CORBA to form a framework for control and transfer of streaming media.
Data distribution management (DDM) is one of the services defined by the DoD High Level Architecture. DDM is necessary to provide efficient, scalable mechanisms for distributing state updates and interaction informati...
详细信息
Data distribution management (DDM) is one of the services defined by the DoD High Level Architecture. DDM is necessary to provide efficient, scalable mechanisms for distributing state updates and interaction information in large scale distributed simulations. We describe data distribution management mechanisms (also known as filtering) used for real time training simulations. We propose a new DDM approach to multicast group allocation, which we refer to as a dynamic grid-based allocation. Our scheme is based on a combination of a fixed grid-based method, known for its low overhead and ease of implementation, and a sender-based strategy, which uses fewer multicast groups than the fixed grid-based method. We describe our DDM algorithm, its implementation, and report on the performance results that we have obtained using the RTI-Kit framework. These results include the outcome of experiments comparing our approach to the fixed grid-based method, and they show that our scheme is scalable and significantly reduces the message overhead of previous grid-based allocation schemes.
Proposes an application framework for mobile agents which provides rule-based generic services to support the three phases of a market transaction (information phase, contracting phase and settlement phase). It is des...
详细信息
Proposes an application framework for mobile agents which provides rule-based generic services to support the three phases of a market transaction (information phase, contracting phase and settlement phase). It is described within the four views of an electronic market (the business view, the transaction view, the services view and the infrastructure view) which describe organizational as well as technological aspects. The focus of this paper is on the technological aspects of the contracting phase in which the participating agents carry out an automated negotiation process to determine the terms of contract.
The vector-clock size necessary to characterize causality in a distributed computation is bounded by the dimension of the partial order induced by that computation. In an arbitrary distributed computation, the dimensi...
详细信息
The vector-clock size necessary to characterize causality in a distributed computation is bounded by the dimension of the partial order induced by that computation. In an arbitrary distributed computation, the dimension can be as large as the width, which in turn can be as large as the number of processes in the computation. Most vector clock algorithms, and all online ones, simply use a vector of size equal to the number of processes. In practice the dimension may be much smaller. It is the purpose of the paper to provide empirical evidence that the dimension of various distributed computations is often substantially smaller than the number of processes. We have found that typical distributed computations, with as many as 300 processes, have dimension less than 10. To achieve this quantification, we developed various theorems and algorithms which we also describe.
The Object Library for parallel Simulation (OLPS) is a set of C++ objects from which a parallel, discrete event simulation or simulation language can be built and run on multiprocessor workstations. OLPS provides a co...
ISBN:
(纸本)9780911801422
The Object Library for parallel Simulation (OLPS) is a set of C++ objects from which a parallel, discrete event simulation or simulation language can be built and run on multiprocessor workstations. OLPS provides a common interface to the simulation programmer for several parallel simulation algorithms, including implementations of the Chandy-Misra and Time-Warp algorithms. OLPS also provides instrumentation to compare the performance of each parallel algorithm on the same simulation problem. The system currently runs on the V distributed system on the DEC Firefly.
This paper examines effective power management of users' stationary desktop PCs in a pervasive computing office environment. The objective being to minimise the building's electricity consumption while maintai...
详细信息
This paper examines effective power management of users' stationary desktop PCs in a pervasive computing office environment. The objective being to minimise the building's electricity consumption while maintaining acceptable desktop PC performance. Current state of the art power management is focused on developing polices for mobile devices, which are ineffective for stationary machines. Effective stationary policies need to obtain context from the user of the machine, but there is a balance between what detail of context is necessary and how much this extra context costs both monetarily and energy wise. We have implemented two location aware policies which detect presence of the user's Bluetooth enabled mobile phone. Trial results indicate that with these policies it is possible to get within 8% of optimal energy consumption with little performance degrade. However, this is the best case and the results are dependent on the user's usage patterns and the geographical layout of the office.
暂无评论