EAGER: Towards a Marketplace for Colocation of Cloud Services

点击翻译按钮获取中文摘要

Cloud computing is transforming our perception of how computing, storage, and networking resources are consumed and managed; yielding improved cost efficiencies, and delivering flexible, on-demand scalability. Along these lines, this project explores the merits of "Colocation Games" (CGs) as a novel, economically-sound framework upon which emerging cloud architectures could be implemented. CGs enable the modeling and analysis of the dynamics that result when rational, selfish parties interact in an attempt to minimize the individual costs they incur to secure the shared cloud resources necessary to support their application QoS or SLA requirements. CGs offer an attractive alternative to approaches that require such parties to trust cloud providers (who may have conflicting incentives), or those that expect such parties to be altruistic or to accept best-effort approaches that do not guarantee performance isolation. In addition to developing the analytical underpinnings of CGs and variants thereof, this project involves the implementation and experimental evaluation of some of these variants for cloud infrastructures, paving the way for the development of a revolutionary distributed resource management alternative for autonomic, self-organizing systems, in which the adoption of a global optimization approach (centralized or distributed) would be neither practical nor justifiable. This project involves the application of techniques from economics to the design of distributed systems. The interdisciplinary training of students along these dimensions promotes technical innovations that are not only cognizant of, but also mitigate the tussle between the various stakeholders of fledgling cloud computing architectures