Esther Pacitti

Reza Akbaranian

Manal El-Dick

As an alternative to traditional client-server systems, Peer-to-Peer (P2P) systems provide major advantages in terms of scalability, autonomy and dynamic behavior of peers, and decentralization of control. Thus, they are well suited for large-scale data sharing in distributed environments. Most of the existing P2P approaches for data sharing rely on either structured networks (e.g., DHTs) for efficient indexing, or unstructured networks for ease of deployment, or some combination. However, these approaches have some limitations, such as lack of freedom for data placement in DHTs, and high latency and high network traffic in unstructured networks. To address these limitations, gossip protocols which are easy to deploy and scale well, can be exploited. In this book, we will give an overview of these different P2P techniques and architectures, discuss their trade-offs, and illustrate their use for decentralizing several large-scale data sharing applications. Table of Contents: P2P Overlays, Query Routing, and Gossiping / Content Distribution in P2P Systems / Recommendation Systems / Top-k Query Processing in P2P Systems

P2P Techniques for Decentralized Applications

A Min Tjoa

Abdelkader Hameurlain

Zoltan Miklos

The LNCS journal Transactions on Large-Scale Data and Knowledge-Centered Systems focuses on data management, knowledge discovery, and knowledge processing, which are core and hot topics in computer science. Since the 1990s, the Internet has become the main driving force behind application development in all domains. An increase in the demand for resource sharing (e.g., computing resources, services, metadata, data sources) across different sites connected through networks has led to an evolution of data- and knowledge-management systems from centralized systems to decentralized systems enabling large-scale distributed applications providing high scalability. This, the 51st issue of Transactions on Large-Scale Data and Knowledge-Centered Systems, contains five fully revised selected regular papers. Topics covered include data anonyomaly detection, schema generation, optimizing data coverage, and digital preservation with synthetic DNA.

Special Issue on Data Management - Principles, Technologies and Applications

Transactions on Large-Scale Data- and Knowledge-Centered Systems LI

Michel Daydé

João Correia Lopes

José M.L.M. Palma

Álvaro L.G.A. Couthino

This book constitutes the thoroughly refereed post-proceedings of the 7th International Conference on High Performance Computing for Computational Science, VECPAR 2006, held in Rio de Janeiro, Brazil, in June 2006. The 44 revised full papers presented together with one invited paper and 12 revised workshop papers cover Grid computing, cluster computing, numerical methods, large-scale simulations in Physics, and computing in Biosciences.

7th International Conference, Rio de Janeiro, Brazil, June 10-13, 2006, Revised Selected and Invited Papers

High Performance Computing for Computational Science - VECPAR 2006

Daniel C. M. De Oliveira

Ji Liu

Workflows may be defined as abstractions used to model the coherent flow of activities in the context of an in silico scientific experiment. They are employed in many domains of science such as bioinformatics, astronomy, and engineering. Such workflows usually present a considerable number of activities and activations (i.e., tasks associated with activities) and may need a long time for execution. Due to the continuous need to store and process data efficiently (making them data-intensive workflows), high-performance computing environments allied to parallelization techniques are used to run these workflows. At the beginning of the 2010s, cloud technologies emerged as a promising environment to run scientific workflows. By using clouds, scientists have expanded beyond single parallel computers to hundreds or even thousands of virtual machines. More recently, Data-Intensive Scalable Computing (DISC) frameworks (e.g., Apache Spark and Hadoop) and environments emerged and are being used to execute data-intensive workflows. DISC environments are composed of processors and disks in large-commodity computing clusters connected using high-speed communications switches and networks. The main advantage of DISC frameworks is that they support and grant efficient in-memory data management for large-scale applications, such as data-intensive workflows. However, the execution of workflows in cloud and DISC environments raise many challenges such as scheduling workflow activities and activations, managing produced data, collecting provenance data, etc. Several existing approaches deal with the challenges mentioned earlier. This way, there is a real need for understanding how to manage these workflows and various big data platforms that have been developed and introduced. As such, this book can help researchers understand how linking workflow management with Data-Intensive Scalable Computing can help in understanding and analyzing scientific big data. In this book, we aim to identify and distill the body of work on workflow management in clouds and DISC environments. We start by discussing the basic principles of data-intensive scientific workflows. Next, we present two workflows that are executed in a single site and multi-site clouds taking advantage of provenance. Afterward, we go towards workflow management in DISC environments, and we present, in detail, solutions that enable the optimized execution of the workflow using frameworks such as Apache Spark and its extensions.

For Clouds and Data-intensive and Scalable Computing Environments

Data-intensive Workflow Management

Esther Pacitti

Books

Your next favorite book is out there