Cloud Resource Scheduling, Monitoring, and Configuration Management in the Software Defined Networking Era

In recent years, Cloud Computing has emerged as a major technology for delivering on-demand IT (Information Technology) services to consumers across the globe [1]. It provides IT resources based on a pay-as-you model and offers a rich set of services and tools. The Cloud Computing stack consists of three layers – Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a service (SaaS). IaaS offers hardware resources (computation, network, and storage) as virtualized cloud services. PaaS provides software services (appliances) and programming tools, whereas SaaS provides ready to use application stacks. In order to ensure bespoke application performance (e.g., minimize response time, maximize throughput); each layer of the Cloud stack requires optimum resource Scheduling, Monitoring, and Configuration-management (SMC). Numerous studies have addressed SMC by proposing various frameworks, models, and algorithms. Most of these studies however have assumed traditional, non-programmable Cloud DataCentre (CDC) networks. In this article, we discuss how resource scheduling, monitoring, and configuration-management becomes a challenging task when considering Software Defined Networking (SDN), and Network Function Virtualisation (NFV) performance parameters as part of overall cloud application scheduling process. The recent technology revolution of so-called Software Defined Networking (SDN) [2] has given full control and programmability of CDC network. Network Function Virtualization (NFV), on other hand, is a recent networking concept often presented with SDN, delivering network services using software processes hosted on CDC-based virtual machines (VMs), instead of proprietary dedicated hardware.