AutoSLAM – A policy‐based framework for automated SLA establishment in cloud environments

Abstract

Welcome to the special issue of Concurrency and Computation: Practice and Experience (CCPE) journal. This special issue compiles a number of excellent technical contributions that significantly advance the state-of-the-art in the areas of orchestrating cloud resources, composing new cloud services from existing ones, increasing energy efficiency via cloud resource orchestration, and developing cloud-based image processing solutions. Over the past few years, cloud computing [1-4] has emerged as the latest and most dominant utility computing solution offering both hardware and software resources as virtualization-enabled services. Cloud computing providers such as Amazon Web Services and Microsoft Azure currently provide application owners the option of deploying their applications over a network of a virtually infinite resource pool with practically no up-front capital investment and with operating cost proportional to the actual use (i.e., implementing a pay-as-you-go model). An increasing number of cloud vendors offer information and communication technology (ICT) resources such as hardware (CPUs, GPUs, storage, and networks), software infrastructure (e.g., databases, webservers, stream-processing systems, and data-mining packages), and collaboration/communication applications (e.g., email, video on demand, and social networks) as infrastructure as a service (IAAS), platform as a service (PAAS), and software as a service (SAAS), respectively. This approach allows enterprises to easily, cost effectively, and reliably offer business services that are supported by computing and software resources that are provided and maintained by IAAS, PAAS, and SAAS providers. This makes cloud computing attractive to especially small and medium size enterprises (SMEs), as it allows them to focus more on their core business and less on ICT infrastructure. One of the fundamental issues in exploiting cloud computing in this fashion is developing better Resource Orchestration (RO) [1-5] techniques and programming frameworks. More specifically, Resource Orchestration (RO) is 'the set of operations that cloud providers (e.g., AWS) and application owners (e.g., Netflix) undertake (either manually or automatically via computer programs) for selecting, deploying, monitoring, and dynamically controlling configuration of hardware and software resources as a system of QoS assured components that can be seamlessly delivered to end-users' [1]. Since RO operations span across all layers of cloud computing stack [1], an overall goal of RO is to ensure successful hosting and delivery of applications (SAAS) by managing the fulfillment of the QoS objectives of both the application owners (e.g., maximize availability, maximize throughput, minimize latency, and avoid overloading) and the Cloud resource providers (e.g., maximize utilization, maximize energy efficiency, and maximize profit). One of the main complexities in Cloud resource management is that Cloud resources are typically identified by unique functional specifications, and then evaluate...