Federated distributed systems (e.g. Grids and Clouds) are inherently large with heterogeneous resource types that may exhibit temporal conditions. They host numerous business and scientific applications. The hard challenges in provisioning these systems include: (i) Scalability - composed of distributed resources (nodes, applications and data) that aggregate together to form a massive environment; (ii) Contention - lack of cooperation among applications and users, particular set of resources can get swamped with excessive workload which undermines the utility delivered by the system; and (iii) Dynamism - resources, applications and users can leave and join the system at will. This book will help in clearly understanding the: (i) taxonomies for designing coordinated and federated distributed systems and their mapping to state-of-the-art techniques and (ii) formulation and implementation of techniques for enforcing coordination, yet ensuring scalability, among distributed platform services (e.g., load-balancers) and users. Although the book considers grid systems as an example, the techniques described here are also applicable to other classes of systems including clouds.
