Applying Machine Learning in Cloud Service Price Prediction: The Case of Amazon IaaS

When exploring alternative cloud solution designs, it is important to also consider cost. Thus, having a comprehensive view of the cloud market and future price evolution allows well-informed decisions to choose between alternatives. Cloud providers offer various service types with different pricing...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Future internet 2023-08, Vol.15 (8), p.277
Hauptverfasser: Fragiadakis, George, Filiopoulou, Evangelia, Michalakelis, Christos, Kamalakis, Thomas, Nikolaidou, Mara
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:When exploring alternative cloud solution designs, it is important to also consider cost. Thus, having a comprehensive view of the cloud market and future price evolution allows well-informed decisions to choose between alternatives. Cloud providers offer various service types with different pricing policies. Currently, infrastructure-as-a-Service (IaaS) is considered the most mature cloud service, while reserved instances, where virtual machines are reserved for a fixed period of time, have the largest market share. In this work, we employ a machine-learning approach based on the CatBoost algorithm to explore a price-prediction model for the reserve instance market. The analysis is based on historical data provided by Amazon Web Services from 2016 to 2022. Early results demonstrate the machine-learning model’s ability to capture the underlying evolution patterns and predict future trends. Findings suggest that prediction accuracy is not improved by integrating data from older time periods.
ISSN:1999-5903
1999-5903
DOI:10.3390/fi15080277