Back to search

Aristotle University Of Thessaloniki (AUTH)

Βελτιστοποίηση ροών εργασιών για ανάλυση δεδομένων

Abstract

dc:description

The big data analysis with the help of automated mechanisms attracts a lot of attention because of the growing need for end-to-end processing of this data. Modern workflows for data analysis, or simply data flows, are adopted in order to process and analyze large volumes of data. However, the data flows become more and more complex and operate in highly dynamic parallel, distributed and heterogeneous environments. This thesis deals with the data flow cost-based optimization and propose task ordering techniques that aim to minimize the total execution cost of the data flow tasks. Additionally, a set of engine selection techniques are proposed for task allocation to specific heterogeneous engines that aim to minimize the flow execution cost. More specifically, the contributions of the thesis are summarized as follows: (i) a thorough survey of data flow optimization research area is presented, (ii) they are presented effective accurate algorithms for finding the optimal order of tasks that minimize the total cost of the flow, (iii) they are proposed for the same problem a set of effective heuristic algorithms that scale for large number of data flow tasks, (iv) a set of effective solutions with low overhead for engine selection among multiple heterogeneous engines is proposed, (v) the proposed techniques are evaluated against the best of the techniques of the state-of-art and finally, (vi) it is proposed a cost model that aims to accurately reflect the response time of a data flow that is executed in parallel.

Degree

thesis:*
Grantor dc:publisher
Aristotle University Of Thessaloniki (AUTH)
Year dc:date
2017

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Kougka, Georgia
  • Κούγκα, Γεωργία

Subjects

dc:subject × 19

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/41309

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

Kougka, Georgia; Κούγκα, Γεωργία. Βελτιστοποίηση ροών εργασιών για ανάλυση δεδομένων. Aristotle University Of Thessaloniki (AUTH), 2017. http://hdl.handle.net/10442/hedi/41309