Abstract
This paper seeks to identify some of the technology challenges and research opportunities in assessing, optimising and assuring performance and dependability on the grid. Grid computing offers many scientific and commercial benefits, but also many technical and organisational challenges. Amongst the challenges for grid computing is the need to provide reliable quality of service to end users, while enabling increasingly dynamic and federated usage scenarios. Understanding and quantifying the performance capabilities of a grid system and its applications is a crucial issue, without which performance improvements will be at best ad hoc. Nevertheless, this is particularly difficult for complex and dynamic systems like the grid, where both the computing environment (in terms of the contributing platforms and networks) and the application base are in continual change. There is an internationally recognised need for research in this area and success will lay the foundation for next generation e-Science.