Article Preview
Top1. Introduction And Motivation
Cloud Computing is a model that allows users to dynamically access and configure a shared pool of computing resources (e.g., networking elements, data storage space, servers, applications and services) over the Internet stored at remote locations. The main enabling technology for Cloud Computing is Virtualization. Cloud computing has revolutionized how software applications are offered to end users, with economies of scale obtained by creating large data centers that provide vast amounts of computation, communication and storage resources. Hence, cloud-based environments are playing an increasingly important role in the context of big data analytics and storage applications. Due to the growth of cloud-based services, users expect on-demand self-service access to applications, infrastructure, and other IT resources. Cloud-based services and applications have enabled massive data centers to exploit the capabilities delivered by Virtualization technologies to increase automation, predictability, efficiency, self-service provisioning, continuity, manageability, quality of service, scalability and flexibility. To efficiently address this increasing demand and rapid growth of Cloud Computing technology, network and service providers need an effective and scalable network solution with significantly low operating costs through simplified hardware, software and management. The Virtualization technology has allowed cloud providers to consolidate the application workloads of a large and diverse set of end-user tenants on a smaller number of physical machines, enabling a high resource utilization while keeping management costs low. However, performance unpredictability in the cloud is a critical issue for many users and it is considered as one of the major obstacles for cloud computing (Armbrust et al., 2009). In this paper, we mainly focus on the role of SDN for scalable cloud-based services and big data applications. The main contributions of this paper are fourfold.
- •
Motivating the direct role of an OpenFlow-enabled SDN for scalable cloud-based services and performance of big data applications from the perspective of future networking.
- •
Exploring a finer and more effective mechanisms in the dimension of bringing SDN and cloud-based services and big data applications together.
- •
Introducing new research and technical challenges in the design and implementation of advanced techniques to use SDN-enabled components in a cloud setting.
- •
Demonstrating the impact of an OpenFlow-enabled SDN that fully embraces the opportunities and challenges of cloud infrastructures to improve the performance of big data applications by taking failure scenarios into account (solving network congestion).
The rest of the paper is structured as follows: In Section 2 we give a brief overview of the role of SDN to the cloud and big data applications. Section 3 provides the system architectures of our study. Section 4 presents the research validation use cases for our study. In Section 6 we discuss the state-of-the-art and related works. Section 7 presents some open research questions to be investigated in greater detail. Finally, Section 8 draws conclusions of the paper and provide an outlook on our intended future work.
Top2. Sdn For Scalable Cloud-Based Services And Big Data Applications
This section presents the role of SDN for scalable cloud-based services and Hadoop-based big data applications.