Resource Management In Cloud And Big Data Systems

<p>Cloud computing is a paradigm shift in computing, where services are offered and acquired on demand in a cost-effective way. These services are often virtualized, and they can handle the computing needs of big data analytics. The ever-growing demand for cloud services arises in many areas including healthcare, transportation, energy systems, and manufacturing. However, cloud resources such as computing power, storage, energy, dollars for infrastructure, and dollars for operations, are limited. Effective use of the existing resources raises several fundamental challenges that place the cloud resource management at the heart of the cloud providers' decision-making process. One of these challenges faced by the cloud providers is to provision, allocate, and price the resources such that their profit is maximized and the resources are utilized efficiently. In addition, executing large-scale applications in clouds may require resources from several cloud providers. Another challenge when processing data intensive applications is minimizing their energy costs. Electricity used in US data centers in 2010 accounted for about 2% of total electricity used nationwide. In addition, the energy consumed by the data centers is growing at over 15% annually, and the energy costs make up about 42% of the data centers' operating costs. Therefore, it is critical for the data centers to minimize their energy consumption when offering services to customers. In this Ph.D. dissertation, we address these challenges by designing, developing, and analyzing mechanisms for resource management in cloud computing systems and data centers. The goal is to allocate resources efficiently while optimizing a global performance objective of the system (e.g., maximizing revenue, maximizing social welfare, or minimizing energy). We improve the state-of-the-art in both methodologies and applications. As for methodologies, we introduce novel resource management mechanisms based on mechanism design, approximation algorithms, cooperative game theory, and hedonic games. These mechanisms can be applied in cloud virtual machine (VM) allocation and pricing, cloud federation formation, and energy-efficient computing. In this dissertation, we outline our contributions and possible directions for future research in this field.</p>

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Open Access Dissertation

Discipline thesis:degree_discipline

Computer Science

Year dc:date.available

2015

Author dc:creator

• Mashayekhy, Lena

Contributors dc:contributor

• Daniel Grosu

• Computer Sciences

Repository record dc:identifier

https://digitalcommons.wayne.edu/oa_dissertations/1345

OAI identifier oai:identifier

oai:digitalcommons.wayne.edu:oa_dissertations-2344