Authors:
Akkarit Sangpetch
;
Orathai Sangpetch
;
Nut Juangmarisakul
and
Supakorn Warodom
Affiliation:
King Mongkut’s Institute of Technology Ladkrabang, Thailand
Keyword(s):
Cloud Computing, Scheduling, Container, Platform-as-a-Service.
Abstract:
Platform-as-a-Service (PaaS) providers often encounter fluctuation in computing resource usage due to
workload changes, resulting in performance degradation. To maintain acceptable service quality, providers
may need to manually adjust resource allocation according to workload dynamics. Unfortunately, this
approach will not scale well as the number of applications grows. We thus propose Thoth, a dynamic
resource management system for PaaS using Docker container technology. Thoth automatically monitors
resource usage and dynamically adjusts appropriate amount of resources for each application. To implement
the automatic-scaling algorithm, we select three algorithms, namely Neural Network, Q-Learning and our
rule-based algorithm, to study and evaluate. The experimental results suggest that Q-Learning can the best
adapt to the load changes, followed by a rule-based algorithm and NN. With Q-Learning, Thoth can save
computing resources by 28.95% and 21.92%, compared to Neural Net
work and the rule-based algorithm
respectively, without compromising service quality.
(More)