Thesis (Ph. D.)--Hong Kong University of Science and Technology, 2002. / Includes bibliographical references (leaves 149-163). Also available in electronic version. Access restricted to campus users.

Thesis (M.S.)--Brigham Young University. Dept. of Computer Science, 2004. / Includes bibliographical references (p. 65-[69]).

Revision of Thesis (Ph. D.)--Stanford, 1979. / Includes bibliographical references (p. [313]-315) and index.

Diss.--Marburg/Lahn. / Cover title. Bibliography: v. 1, leaves 203-210.

Thesis (M.S.)--Worcester Polytechnic Institute. / Keywords: Java; weak reference; reference objects; distributed objects; distributed garbage collection. Includes bibliographical references (p. 91-93).

Thesis (M.S.)--University of Florida, 2002. / Title from title page of source document. Includes vita. Includes bibliographical references.

Thesis (Ph. D.)--Ohio State University, 2003. / Title from first page of PDF file. Document formatted into pages; contains xvii, 172 p.; also includes graphics. Includes abstract and vita. Advisor: Dhabeleswar K. Panda, Dept. of Computer and Information Science. Includes bibliographical references (p. 167-172).

Cloud computing has rapidly emerged as a new computation paradigm, providing agile and scalable resource access in a utility-like fashion. Processing of massive amounts of data has been a primary usage of the clouds in practice. While many efforts have been devoted to designing the computation models (e.g., MapReduce), one important issue has been largely neglected in this respect: how do we efficiently move the data, practically generated from different geographical locations over time, into a cloud for effective processing? The usual approach of shipping data using hard disks lacks flexibility and security. As the first dedicated effort, this paper tackles this massive, dynamic data migration issue. Targeting a cloud encompassing disparate data centers of different resource charges, we model the cost-minimizing data migration problem, and propose efficient offline and online algorithms, which optimize the routes of data into the cloud and the choice of the data center to aggregate the data for processing, at any give time. Three online algorithms are proposed to practically guide data migration over time. With no need of any future information on the data generation pattern, an online lazy migration (OLM) algorithm achieves a competitive ratio as low as 2:55 under typical system settings, and a work function algorithm (WFA) has a linear 2K-1 (K is the number of data centers) competitive ratio. The rest one randomized fixed horizon control algorithm (RFHC) achieves 1+ 1/(l+1 ) κ/λ competitive ratio in theory with a lookahead window of l into the future, where κ and λ are protocol parameters. We conduct extensive experiments to evaluate our online algorithms, using real-world meteorological data generation traces, under realistic cloud settings. Comparisons among online and offline algorithms show a close-to-offline-optimum performance and demonstrate the effectiveness of our online algorithms in practice. / published_or_final_version / Computer Science / Master / Master of Philosophy

Along with the rapid growth of Wireless Sensor Networks, a wide range of challenges have come to existence to make the network more robust and versatile. Gaining energy efficiency and maximizing network lifetime are the most important of all that can affect the performance of the network directly. In this thesis, a number of research aspects related to energy efficient data gathering have been investigated and some promising proposals are presented. In large, hierarchical multi-hop Wireless Sensor Networks, power consumption characteristics of the static sensor nodes and data traffic distribution across the network are largely determined by the node position and the adopted routing protocol. In this thesis, these phenomena of the network are addressed analytically and we proposed some methods to divide the monitoring field into partitions that act as the basis for even load distribution in the network. We proposed an algorithm to calculate the area of the partitions that exploits the energy efficient features of optimal transmission range. The partition works as the bedrock of the other proposals in this thesis. Considering the influential factors of the proximity and the recent state of the network, we also developed a routing protocol that minimises over all energy consumption of the network and is able to dynamically select a route to the sink. Further, we proposed a rotational order for data gathering scheme that works along with the routing protocol to ensure load balancing and to alleviate data congestion around the sink. Clustered organization of the nodes in sensor networks can further save energy consumption and facilitates scope for better network management. In this thesis, we address the fact that equal sized clusters can cause unbalanced data traffic around the sink. So, we propose a method to calculate suitable cluster radii in different regions of the monitoring field in order to form clusters of different sizes. To ensure unequal clusters in the field, a cluster construction procedure is also proposed targeting minimal data generation, minimal energy consumption and providing capacity for reliability preservation. Furthermore, the notion of redundant nodes and the outlines of a possible solution to identify and deactivate redundant nodes are explained in this thesis. Since the clusterheads play an important role as coordinators in the clusters, it is vital that there is a clusterhead in every cluster all the time. In this thesis, a message optimal and distributed leader election algorithm is proposed to select a new clusterhead in case of unexpected and unnoticed failure of a clusterhead node. Detailed analysis and simulation of the proposed methods clarify the effectiveness of the research. In comparison with other methods of similar kind, our methods confirm better balanced energy dissipation, energy efficient route selection, message optimal clusterhead selection and prolonged lifetime of the network.

published_or_final_version / Computer Science / Master / Master of Philosophy