Open Access

ARTICLE

Light-Weighted Decision Support Framework for Selecting Cloud Service Providers

by Abdulmajeed Aljuhani^1,*, Abdulaziz Alhubaishy², Mohammad Khalid Imam Rahmani², Ahmad A. Alzahrani³

1 College of Computer Science and Engineering, Taibah University, Medina, 41411, Saudi Arabia
2 College of Computing and Informatics, Saudi Electronic University, Riyadh, 11673, Saudi Arabia
3 Computer Science, Common First Year Deanship, Umm-AlQura University, Makkah, MK, Saudi Arabia

* Corresponding Author: Abdulmajeed Aljuhani. Email:

Computers, Materials & Continua 2023, 74(2), 4293-4317. https://doi.org/10.32604/cmc.2023.033893

Received 30 June 2022; Accepted 27 August 2022; Issue published 31 October 2022

Abstract

Multi-criteria decision making (MCDM) is a technique used to achieve better outcomes for some complex business-related problems, whereby the selection of the best alternative can be made in as many cases as possible. This paper proposes a model, the multi-criteria decision support method, that allows both service providers and consumers to maximize their profits while preserving the best matching process for resource allocation and task scheduling. The increasing number of service providers with different service provision capabilities creates an issue for consumers seeking to select the best service provider. Each consumer seeks a service provider based on various preferences, such as price, service quality, and time to complete the tasks. In the literature, the problem is viewed from different perspectives, such as investigating how to enhance task scheduling and the resource allocation process, improve consumers’ trust, and deal with network problems. This paper offers a novel model that considers the preferences of both service providers and consumers to find the best available service provider for each consumer. First, the model adopts the best-worst method (BWM) to gather and prioritize tasks based on consumers’ and service providers’ preferences. Then, the model calculates and matches similarities between the sets of tasks from the consumer’s side with the sets of tasks from the provider’s side to select the best service provider for each consumer using the two proposed algorithms. The complexity of the two algorithms is found to be O(n³).

---

Keywords

---