The talk will argue for the need to use autonomic computing techniques to improve performance in volatile environments, such as those typically associated with Grids and large-scale distributed computing, using a systematic approach to manage their dynamic nature. The realization of autonomic computing is based on having a feedback loop that monitors the environment, makes assessments and acts if needed. Different approaches to implement decision making mechanisms in this feedback loop, ranging from control theory to utility functions, will be discussed and illustrated using specific examples drawn from research in the context of UK and European projects. The talk will conclude with some challenges in the area.
Rizos Sakellariou is with the University of Manchester, UK, from where he obtained his PhD in 1997. He has also held positions with Rice University and the University of Cyprus and visiting appointments with the University of Illinois and the Universitat Politecnica de Catalunya. His research interests fall in the wide area of High-Performance Parallel, Distributed and Grid Computing. For more info see at http://www.cs.man.ac.uk/~rizos/
