Integrating Bayesian Optimization and Machine Learning for the Optimal Configuration of Cloud Systems

Bayesian Optimization (BO) is an efficient method for finding optimal cloud configurations for several types of applications. On the other hand, Machine Learning (ML) can provide helpful knowledge about the application at hand thanks to its predicting capabilities. This work proposes a general appro...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on cloud computing Ročník 12; číslo 1; s. 277 - 294
Hlavní autoři: Guindani, Bruno, Ardagna, Danilo, Guglielmi, Alessandra, Rocco, Roberto, Palermo, Gianluca
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Acquisition function
Algorithms
Bayes methods
Bayesian analysis
Bayesian optimization
Black boxes
black-box optimization
Closed box
Cloud computing
Computational modeling
Configurations
Costs
Edge computing
Machine learning
Optimization
Software algorithms
ISSN:2168-7161, 2372-0018
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Bayesian Optimization (BO) is an efficient method for finding optimal cloud configurations for several types of applications. On the other hand, Machine Learning (ML) can provide helpful knowledge about the application at hand thanks to its predicting capabilities. This work proposes a general approach based on BO, which integrates elements from ML techniques in multiple ways, to find an optimal configuration of recurring jobs running in public and private cloud environments, possibly subject to black-box constraints, e.g., application execution time or accuracy. We test our approach by considering several use cases, including edge computing, scientific computing, and Big Data applications. Results show that our solution outperforms other state-of-the-art black-box techniques, including classical autotuning and BO- and ML-based algorithms, reducing the number of unfeasible executions and corresponding costs up to 2-4 times.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2168-7161
2372-0018
DOI:10.1109/TCC.2024.3361070