Autonomic Computing Middleware

Sponsored by NSF NGS program




The overall research objective of this project is to investigate key technologies that will enable the development of Autonomic Grid Applications that are context aware and are capable of self-configuring, self-composing, self-optimizing and self-adapting. Specifically, it investigates the definition of autonomic components, the development of autonomic applications as dynamic composition of autonomic components, and the design of key enhancements to existing Grid middleware and runtime services to support these applications on the Grid. This project is sponsored by NSF NGS CNS-0305427. The efforts have also leveraged support from the following grants: Scientific Discovery through Advanced Computing (SciDAC) program of the DOE, grant number DE-FC02-01ER41184, and Intel Corporation IT R&D Council. This project is related to our Adaptive Fusion of Stochastic Information for Imaging Fractured Vadose Zones project.

Research Activities:

1. AUTONOMIA : An Autonomic Computing Environment

Project Autonomia investigates the autonomic computing approach, which is based on the strategies used by biological systems to deal with complexity, dynamism, heterogeneity and uncertainty. This approach aims to realize computing systems and applications capable of managing themselves with minimum human intervention, such as self-configuring, self-optimizing, self-healing, self-protecting, etc.

2. Self-Optimization of Large Scale Wildfire Simulation

The development of efficient parallel algorithms for large scale wildfire simulations is a challenging research problem because the factors that determine wildfire behavior are complex; they include fuel characteristics and configurations, chemical reactions, balances between different modes of heat transfer, topography, and fire/atmosphere interactions. These factors make static parallel algorithms inefficient, especially when large number of processors is used. By dynamically exploiting the physics properties of the fire simulation at run time, the Autonomic Runtime Manager (ARM) can accomplish self-optimization of the wild fire simulation.

This project is sponsored by NSF Gransts number 0431079