Cloud Computing: Principles and Paradigms

Chapter 15. AN ARCHITECTURE FOR FEDERATED CLOUD COMPUTING

BENNY ROCHWERGER, CONSTANTINO VÁZQUEZ, DAVID BREITGAND, DAVID HADAS, MASSIMO VILLARI, PHILIPPE MASSONET, ELIEZER LEVY, ALEX GALIS, IGNACIO M. LLORENTE, RUBÉN S. MONTERO, YARON WOLFSTHAL, KENNETH NAGIN, LARS LARSSON, and FERMÍN GALÁN

INTRODUCTION

Utility computing, a concept envisioned back in the 1960s, is finally becoming a reality. Just as we can power a variety of devices, ranging from a simple light bulb to complex machinery, by plugging them into the wall, today we can satisfy, by connecting to the Internet, many of our computing needs, ranging from full pledge productivity applications to raw compute power in the form of virtual machines. Cloud computing [1], in all its different forms, is rapidly gaining momentum as an alternative to traditional IT, and the reasons for this are clear: In principle, it allows individuals and companies to fulfill all their IT needs with minimal investment and controlled expenses (both capital and operational).

Cloud computing enables companies and individuals to lease resources on-demand from a virtually unlimited pool. The "pay as you go" billing model applies charges for the actually used resources per unit time. This way, a business can optimize its IT investment and improve availability and scalability.

While cloud computing holds a lot of promise for enterprise computing, there are a number of inherent deficiencies in current offerings such as:

• Inherently Limited Scalability of Single-Provider ...