<div class="csl-bib-body">
<div class="csl-entry">Mayerhofer, R. (2023). <i>Reinforcement-learning-based, application-agnostic, and explainable auto-scaling in the cloud utilizing high-level SLOs</i> [Diploma Thesis, Technische Universität Wien]. reposiTUm. https://doi.org/10.34726/hss.2023.106505</div>
</div>
-
dc.identifier.uri
https://doi.org/10.34726/hss.2023.106505
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/188210
-
dc.description.abstract
Cloud computing is a widely adopted paradigm in the software industry. The ability to adapt the provisioned resources for an application based on the actual demand is called auto-scaling. Auto-scaling is crucial to keep costs within limits while ensuring sufficient performance. Effective auto-scaling is a multi-dimensional problem and an active area of research. The industry standard for auto-scaling is static thresholds based on low-level metrics such as CPU utilization, while researchers are experimenting with applying Machine Learning techniques to auto-scaling. Static thresholds are hard to set up and need to be manually corrected, and low-level metrics are disconnected from the business goals. On the other hand, Reinforcement Learning is a popular approach to autonomously learning an auto-scaling policy. While promising, RL introduces new problems to the auto-scaling domain, such as a lack of explainability and interpretability, complexity, long learning phases, and bad worst-case performance. We aim to find ways to efficiently auto-scale while bridging the gap between auto-scaling and business goals without the undesirable properties of RL solutions.This thesis presents two approaches to auto-scaling, Extended-Q-Threshold, and HPA-Q-Threshold, both building upon Q-Threshold, an auto-scaling system from the literature. Our auto-scalers are integrated into the Polaris framework, built with a flexible architecture in mind. We extend and adapt Q-Threshold, an approach to auto-scaling where the RL agent controls the usually static threshold, effectively making it dynamic. Our adaptations tackle experimentally identified shortcomings of the Q-Threshold approach. Furthermore, we generalize the approach and apply different scaling metrics and rewards. Thus, we enable the further development and evaluation of this promising approach.We show how a modern, flexible auto-scaler can be integrated with the Polaris framework and run in a Kubernetes cluster. Our experiments evaluate the effectiveness of our proposed adaptations and prove that some are necessary to prevent the identified issues of Q-Threshold. In contrast, others must be carefully assessed and tested, such as different scaling metrics and reward definitions. Overall, the adaptations help ensure the interpretability of the auto-scaler by utilizing a very lightweight implementation of RL. Furthermore, our auto-scaler possesses other positive characteristics, such as limiting the worst-case and guaranteeing acceptable early-stage performance.
en
dc.language
English
-
dc.language.iso
en
-
dc.rights.uri
http://rightsstatements.org/vocab/InC/1.0/
-
dc.subject
Auto scaling
en
dc.subject
Service Level Objective
en
dc.subject
Reinforcement Learning
en
dc.subject
Q-learning
en
dc.subject
Q-Threshold
en
dc.subject
Polaris framework
en
dc.subject
Cloud Elasticity
en
dc.title
Reinforcement-learning-based, application-agnostic, and explainable auto-scaling in the cloud utilizing high-level SLOs
en
dc.type
Thesis
en
dc.type
Hochschulschrift
de
dc.rights.license
In Copyright
en
dc.rights.license
Urheberrechtsschutz
de
dc.identifier.doi
10.34726/hss.2023.106505
-
dc.contributor.affiliation
TU Wien, Österreich
-
dc.rights.holder
Robin Mayerhofer
-
dc.publisher.place
Wien
-
tuw.version
vor
-
tuw.thesisinformation
Technische Universität Wien
-
dc.contributor.assistant
Morichetta, Andrea
-
tuw.publication.orgunit
E194 - Institut für Information Systems Engineering
-
dc.type.qualificationlevel
Diploma
-
dc.identifier.libraryid
AC16940127
-
dc.description.numberOfPages
92
-
dc.thesistype
Diplomarbeit
de
dc.thesistype
Diploma Thesis
en
dc.rights.identifier
In Copyright
en
dc.rights.identifier
Urheberrechtsschutz
de
tuw.advisor.staffStatus
staff
-
tuw.assistant.staffStatus
staff
-
tuw.advisor.orcid
0000-0001-6872-8821
-
tuw.assistant.orcid
0000-0003-3765-3067
-
item.cerifentitytype
Publications
-
item.openairetype
master thesis
-
item.mimetype
application/pdf
-
item.fulltext
with Fulltext
-
item.languageiso639-1
en
-
item.openairecristype
http://purl.org/coar/resource_type/c_bdcc
-
item.grantfulltext
open
-
item.openaccessfulltext
Open Access
-
crisitem.author.dept
E194 - Institut für Information Systems Engineering