Cloud Computing: Architectural and Policy Implications

Abstract

Cloud computing has emerged as perhaps the hottest development in information technology. Despite all of the attention it has garnered, existing analyses focus almost exclusively on the issues surrounding data privacy without exploring cloud computing’s architectural and policy implications. This Article offers an initial exploratory analysis in that direction. It begins by introducing key cloud computing concepts, such as service oriented architectures, thin clients, and virtualization, and discusses the leading delivery models and deployment strategies being pursued by cloud computing providers. It then analyzes the economics of cloud computing in terms of reducing costs, transforming capital expenditures into operating expenditures, aggregating demand, increasing reliability, and reducing latency. It then discusses the architectural implications of cloud computing for access networking (focusing on bandwidth, reliability, quality of service, and ubiquity) and data center interconnectivity (focusing on bandwidth, reliability, security and privacy, control over routing policies, standardization, and metering and payment). It closes by offering a few observations on the impact of cloud computing on the industry structure for data centers, server-related technologies, router-based technologies, and access networks, as well as its implications for regulation.