Back to search

University of Patras

Monitoring and control of distributed web services on cloud computing infrastructure

Abstract

dc:description

This thesis concern two main research areas of distributed web services deployed on cloud computing infrastructure.The first part is about monitoring of cloud computing infrastructure. A novel general technique is used to infer relationships between different service components in a data center. This approach relies on a small set of fuzzy rules, produced by a hybrid genetic algorithm with high classification rate. Furthermore, the strength of detected dependencies is measured This approach can be a useful monitoring tool for administrators to obtain a clear view of what is happening in the underlying network. The second major problem is the automated resource control of consolidated web applications on cloud computing infrastructure. ACRA (Admission Control and Resource Allocation) is an autonomic modeling and control framework that provides accurate modeling, joint admission control and capacity allocation among different consolidated services on cloud computing data centers. The objective is to maximize the provider’s revenue (by maximizing admittance of customers to the provided service), while fulfilling QoS requirements. The second local level controller of the thesis is an autonomous modeling and control framework that solves admission control and resource allocation simultaneously in a unified way. In specific, a Linear Parameter Varying (LPV) state space model is adopted to capture the dynamic behavior of the underlying infrastructure. The operating conditions are determined according to an optimization criterion. A feasible operating point, which satisfies the desired QoS nominal values, is computed. The resulting stabilizing state feedback control law is an affine state-dependent control law that can be easily implemented. The computational complexity of the controller implementation is small, since at every time instant only a linear program and a point location problem are solved. Finally, convergence to the feasible operating point and satisfaction of the system’s constraints are guaranteed, for a number of desired operating points of interest.

Degree

thesis:*
Grantor dc:publisher
University of Patras
Year dc:date
2014

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Dechouniotis, Dimitrios
  • Δεχουνιώτης, Δημήτριος

Subjects

dc:subject × 10

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/31587

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Dechouniotis, Dimitrios; Δεχουνιώτης, Δημήτριος. Monitoring and control of distributed web services on cloud computing infrastructure. University of Patras, 2014. http://hdl.handle.net/10442/hedi/31587