English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Autonomic Computing is an emerging research area which deals with systems capable of self-managing their tasks in an intelligent, dynamic and automatic manner. It addresses the increasing complexity of current computing systems, which become more and more di cult to integrate and maintain, mainly due to their scale growth and the need for specialized labor. Grid computing requires self-manageable features, essentially due to the complexity associated to its task dynamical behavior, information sharing, di erent user pro les, geographically distributed resources and heterogeneity. The need for those features has encouraged many research e orts, most of them focused on proposing autonomic architectures (structuring components to provide services) and the integration of tools and services. Few research initiatives address the study, design and evaluation of techniques and models to support and improve grid autonomic aspects. This scenario has motivated the Middleware for High Performance Computing (MidHPC) project which investigates self-manageable supports for data distribution, fault tolerance, security and process scheduling. Promising results were obtained by considering historical resource consumption averages. Results encouraged additional e orts to assess process behavior variations and their application to improve autonomic aspects of grid computing. Comprehension of those variations in behavior motivated this thesis, which employs dynamical system concepts and intelligent techniques to model and predict process behavior, aiming at optimizing scheduling operations in grid computing environments. Process communication operations were predicted and used to parameterize a new process scheduling policy which attempts to minimize communication and processing costs. This policy was compared to others from the literature. Results con rm relevant contributions and motivate the adoption of the proposed approach to improve other grid autonomic aspects.

Sistemas dinâmicos e técnicas inteligentes para a predição de comportamento de processos: uma abordagem para otimização de escalonamento em grades computacionais