Applying queue theory for modeling of cloud computing: A systematic review

Abstract

The cloud computing paradigm is an important service in the Internet for sharing and providing resources in a cost-efficient way. Modeling of a cloud system is not an easy task because of the complexity and large scale of such systems. Cloud reliability could be improved by modeling the various aspects of cloud systems, including scheduling, service time, wait time, and hardware and software failures. The aim of this study is to survey research studies done on the modeling of cloud computing using the queuing system in order to identify where more emphasis should be placed in both current and future research directions. This paper follows the goal by investigating the articles published between 2008 and January 2017 in journals and conferences. A systematic mapping study combined with a systematic literature review was performed to find the related literature, and 71 articles were selected as primary studies that were classified in relation to the focus, research type, and contribution type. We classified the modeling techniques of cloud computing using the queuing theory in seven categories based on their focus area: (1) performance, (2) quality of service, (3) workflow scheduling, (4) energy savings, (5) resource management, (6) priority-based servicing, and (7) reliability. A majority of the primary articles focus on performance (37%), 15% of them focus on resource management, 14% of them focus on quality of service, 13% of them focus on workflow scheduling, 13% of them focus on energy savings, 4% of them focus on priority-based servicing for requests, and 4% of them focus on reliability. This work summarizes and classifies the research efforts conducted on applying queue theory for modeling of cloud computing (AQTMCC), providing a good starting point for further research in this area. KEYWORDScloud computing, cloud modeling, queuing systems, queuing theory, systematic review INTRODUCTIONCloud computing is the recent evolution in the information technology and is growing very fast due to the extensive use of mobile devices, such as PDAs, cell phones, and tablets. 1 To emphasize the goals of cloud computing, we refer to the definition of NIST (National Institute of Standards and Technology); a cloud model is composed of five characteristics, three service models, and four deployment models. 2 Service models of cloud computing are as follows: (1) Software as a Service (SaaS), such as CRM (Customer Relationship Management), virtual desktop, communications, and games; (2) Platform as a Service (PaaS), such as databases, web servers, and deployment tools; and (3) Infrastructure as a Service (IaaS), such as virtual machines (VMs), storages, servers, and load balancers. Deployment models include private clouds, public clouds, community clouds, and hybrid clouds. The characteristics of a cloud are on-demand self-servicing, elasticity, broad network access, resource pooling, and measured service. 1 A data center in cloud computing consists of several servers that are organized in racks and connected through communicati...

Resource allocation mechanisms in cloud computing: a systematic literature review

“… What is the role of RA in cloud computing and its importance for cloud computing researchers? What modules does a resource management system (RMS) consist of? Based on what parameters can an RA mechanism be categorised? How many recent research studies have been made in the field of RA? What tools have researchers used to evaluate the results of RA mechanisms? What challenges and open issues remain in the field of RA and what issues are currently covered? This research started in 2016. The primary methodology and strategy of this paper are based on our previous review papers [4–16 ]. For a systematic presentation of this paper, the mechanisms have been proposed based on their published years and their databases.…”

IoT Sensor Networks in Smart Buildings: A Performance Assessment Using Queuing Models

“…Queuing theory is a powerful analytical model that can represent complex systems [ 24 , 27 , 42 , 43 ]. This section presents a model based on queuing theory for the presented architecture, which is illustrated in Figure 4 .…”

“…Queue models are simple, didactic and efficient [ 24 , 25 , 26 ]. Queue theory applications generally have two goals: predicting system performance and finding a system design to improve performance in the planning phase [ 27 ].…”

Delay Analysis in IoT Sensor Networks

“…In terms of analysis, the work in [ 13 ] surveys the research efforts conducted on applying queuing theory to model and analyze cloud computing. In [ 14 ], an approach in the context of queue was developed to analyze a data center with heterogeneous servers.…”