We propose a novel approach to select IaaS cloud services for a long-term period where the service providers offer limited QoS information. The proposed approach leverages free short-term trials to obtain the previously undisclosed QoS information. A new significance-based trial scheme is proposed using frequency distribution analysis to test a consumer's long-term workloads in a short trial. We introduce a novel IaaS signature technique to uniquely identify the variability of a provider's QoS performance. A Signature-based QoS Performance Discovery (SPD) algorithm is proposed which leverages the combination of free trials and IaaS signatures. A set of exhaustive experiments with real-world datasets is conducted to evaluate the proposed approach.
@article{arxiv.2004.12378,
title = {Signature-based Selection of IaaS Cloud Services},
author = {Sheik Mohammad Mostakim Fattah and Athman Bouguettaya and Sajib Mistry},
journal= {arXiv preprint arXiv:2004.12378},
year = {2020}
}
Comments
8 pages, Accepted and to appear in 2020 IEEE International Conference on Web Services (ICWS). Content may change prior to final publication