Auction‐based resource allocation mechanisms in the cloud environments: A review of the literature and reflection on future challenges

Abstract

Cloud computing is an Internet-based computing and networking model, with elasticity and scalability capabilities where the services are delivered to its users in a non-demand style. In this computing paradigm, the request and response between users and providers must be managed using the resource allocation strategies. Therefore, allocating the provided resources to the users based on their needs is the important challenge in this environment. Also, an auction in the cloud is a process of buying and vending the cloud services by offering them up for bid and then selling the service to the highest bidder. However, to the best of our knowledge, there has not been any comprehensive and detailed paper about reviewing the state-of-the-art mechanisms on this important topic and providing open issues as well. Hence, this paper provides a comprehensive survey and review of the auction-based resource allocation mechanisms, which have been employed in the cloud environments up to now. Also, we classified the important cloud resource allocation mechanisms into four categories: one-sided, double-sided, combinatorial, and other types of auction-based mechanisms. Moreover, we reviewed the main progress in these four categories and defined the new issues. Finally, the paper offers the differences among reviewed mechanisms as well as guidelines for future investigation.

Task scheduling in Internet of Things cloud environment using a robust particle swarm optimization

“…21 Typically, resource allocation in JSP is considered as an optimization problem, and several heuristic algorithms have been proposed based on different assumptions and constraints. 18,[22][23][24][25][26][27][28] These algorithms directly influence the volume, frequency, and intensity of data exchange in job-shop as well as the scheduling quality. 21 Most of heuristic algorithms can be classified into three types with respect to the real-time processing.…”

A fuzzy logic‐based method for solving the scheduling problem in the cloud environments using a non‐dominated sorted algorithm

“…In the first scenario, which is denoted as S1, the number of all tasks (n) and the number of all resources (m) are assigned (12,2). In the second scenario, which is denoted as S2, the number of all tasks (n) and the number of all resources (m) are assigned (20,3).…”

Deterministic and non‐deterministic query optimization techniques in the cloud computing

“…8,9 The cloud computing gives shared access to a large pool of resources, including data storage, memory, processing, and virtual machines. 8,9 The cloud computing gives shared access to a large pool of resources, including data storage, memory, processing, and virtual machines.…”

“…The query optimizer attempts to provide the most optimal execution plan by considering the possible query plans. 8,9 The cloud computing gives shared access to a large pool of resources, including data storage, memory, processing, and virtual machines. In addition, it is known as NP-hard problem and many researchers are focused on this problem in recent years.…”

“…7This paradigm provides many benefits for users, such as the provision of computing capabilities, heterogeneous network access, scalability, and elasticity with measured services. 8,9 The cloud computing gives shared access to a large pool of resources, including data storage, memory, processing, and virtual machines. 10 A cloud client, such as a web browser and mobile app can be helpful in accessing these services.…”