Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Introduction Computer science applications are becoming more and more network centric, ubiquitous, knowledge intensive, and computing demanding. This trend will result soon in an ecosystem of pervasive applications and services that professionals and end-users can exploit everywhere. Recently, collections of IT services and applications, such as Web services and Cloud computing services, became available opening the way for accessing computing services as public utilities, like water, gas and electricity. Key technologies for implementing that perspective are Cloud computing and Web services, semantic Web and ontologies, pervasive computing, P2P systems, Grid computing, ambient intelligence architectures, data mining and knowledge discovery tools, Web 2.0 facilities, mashup tools, and decentralized programming models. In fact, it is mandatory to develop solutions that integrate some or many of those technologies to provide future knowledge-intensive software utilities. The Grid paradigm can represent a key component of the future Internet, a cyber infrastructure for efficiently supporting that scenario. Grid and Cloud computing are evolved models of distributed computing and parallel processing technologies. The Grid is a distributed computing infrastructure that enables coordinated resource sharing within dynamic organizations consisting of individuals, institutions, and resources. In the area of Grid computing a proposed approach in accordance with the trend outlined above is the Service-Oriented Knowledge Utilities (SOKU) model that envisions the integrated use of a set of technologies that are considered as a solution to information, knowledge and communication needs of many knowledge-based industrial and business applications. The SOKU approach stems from the necessity of providing knowledge and processing capabilities to everybody, thus supporting the advent of a competitive knowledge-based economy. Although the SOKU model is not yet implemented, Grids are increasingly equipped with data management tools, semantic technologies, complex work-flows, data mining features and other Web intelligence approaches. Similar efforts are currently devoted to develop knowledge and intelligent Clouds. These technologies can facilitate the process of having Grids and Clouds as strategic components for supporting pervasive knowledge intensive applications and utilities. Grids were originally designed for dealing with problems involving large amounts of data and/or compute-intensive applications. Today, however, Grids enlarged their horizon as they are going to run business applications supporting consumers and end-users. To face those new challenges, Grid environments must support adaptive knowledge management and data analysis applications by offering resources, services, and decentralized data access mechanisms. In particular, according to the service-oriented architecture (SOA) model, data mining tasks and knowledge discovery processes can be delivered as services in Grid-based infrastructures. Through a service-based approach we can define integrated services for supporting distributed business intelligence tasks in Grids. Those services can address all the aspects that must be considered in data mining and in knowledge discovery processes such as data selection and transport, data analysis, knowledge models representation and visualization. We worked in this direction for providing Grid-based architectures and services for distributed knowledge discovery such as the Knowledge Grid the Weka4WS toolkit, and mobile Grid services for data mining. Here we describe a strategy and a model based on the use of services for the design of distributed knowledge discovery services and discuss how Grid frameworks, such those mentioned above, can be developed as a collection of services and how they can be used to develop distributed data analysis tasks and knowledge discovery processes using the SOA model.
Scientists increasingly rely on the execution of workflows in grids to obtain results from complex mixtures of applications. However, the inherently dynamic nature of grid workflow scheduling, stemming from the unavailability of scheduling information and from resource contention among the (multiple) workflows and the non-workflow system load, may lead to poor or unpredictable performance. In this paper we present a comprehensive and realistic investigation of the performance of a wide range of dynamic workflow scheduling policies in multicluster grids. We first introduce a taxonomy of grid workflow scheduling policies that is based on the amount of dynamic information used in the scheduling process, and map to this taxonomy seven such policies across the full spectrum of information use. Then, we analyze the performance of these scheduling policies through simulations and experiments in a real multicluster grid. We find that there is no single grid workflow scheduling policy with good performance across all the investigated scenarios. We also find from our real system experiments that with demanding workloads, the limitations of the head-nodes of the grid clusters may lead to performance loss not expected from the simulation results. We show that task throttling, that is, limiting the per-workflow number of tasks dispatched to the system, prevents the head-nodes from becoming overloaded while largely preserving performance, at least for communication-intensive workflows.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.