Detail

Publication date: 1 de June, 2021

Workshop on Autonomic Computational Science, held in conjunction with IEEE/ACM Grid2010 – The 11th ACM/IEEE International Conference on Grid Computing, Brussels (October 2010)

Strategic investments coupled with technological advances are rapidly realizing a pervasive cyberinfrastructure, both nationally and globally, that integrates computers, networks, data archives, instruments, observatories, experiments, and embedded sensors and actuators. Such a computational ecosystem has the potential to catalyze new thinking in virtually all areas of computational science and engineering, which can lead to unprecedented insights into natural, engineered and human systems. For example, application formulations can holistically investigate any phenomena of interest by combining computations, experiments, observations, and real-time information, for example, to understand and manage natural and engineered systems. These emerging computational paradigms and practices enabled by this cyber-ecosystem are naturally distributed and collaborative and fundamentally data intensive and data driven, as they explore coupled multi-physics, multi-scale formulations, end-to-end application workflows.

Autonomic computing techniques can address various aspects of system behaviour in the context of such infrastructure. Central to the autonomic paradigm are three fundamental separations: (1) a separation of computations from coordination and interactions; (2) a separation of non-functional aspects (e.g. resource requirements, performance) from functional behaviors, and (3) a separation of policy and mechanism – policies in the form of rules are used to orchestrate a repertoire of mechanisms to achieve context-aware adaptive runtime computational behaviors and coordination and interaction relationships based on functional, performance, and Quality of Service requirements. For instance, Autonomic computing techniques could provide:

New and more robust application formulation
Management of unpredictable system behaviour and unforeseen user behaviour and abuse;
Better management of energy consumption; and
More effective resource management to support scalability so that resources behave “elastically” at higher usage levels.

The aim of this workshop is to seek contributions in: (i) application construction; (ii) infrastructure management, that could facilitate the development of computational science applications over dynamic, unreliable and heterogeneous infrastructure.

---