Cloud computing offers ubiquitous, on-demand services over the Internet as a utility, providing users configurable resources, infrastructure scaling, and minimal upfront cost. Yet, it faces many challenges in network topologies, network security, and resource scheduling. Hence, testbeds are used to test different solutions based on these challenges. Testbeds are a realistic setup of a particular hardware-software environment where applications and frameworks can be studied for functional performance and operational efficiency. The most common tool for creating testbeds is OpenStack, as it is open-sourced, scalable, and flexible. This work organizes the recent developments in the domain and implements an OpenStack testbed for evaluating its applicability. The findings of this review suggest that OpenStack supports the development of testbeds for enterprises and independent researchers by offering varying levels of configuration and modularity to satisfy specific requirements. Metric collection tools such as the Ceilometer can facilitate planning, protection, and preventative measures.

Academic Research Computing Clouds are widely deployed worldwide by research institutions to support researcher's computations. While the nature of the hosted use-cases is diverse, literature and institutions' published guides point to highly parallel HPC workloads and state-heavy workloads as two popular use-cases in research-computing clouds. Additionally, our prior investigation has uncovered unique patterns in the users' VM-provisioning behaviors in four of Canada's research-computing clouds. These patterns, i.e., usage-trends, were generated by examining nearly 1 million VMs created by researchers over four and half years. The usage trends mimicked behaviors of provisioning highly parallel HPC workloads and state-heavy portals. In this paper, we exploit the knowledge of these usage trends to guide VM placement decisions in research-computing IaaS clouds. We propose a delayed-provisioning algorithm that postpones resource allocations for incoming VM requests in anticipation of running VMs termination, minimizing the number of active PMs and PM underutilization. We examine the performance of the proposed algorithm compared to other placement algorithms using a real-life validation dataset of nearly 850 thousand VMs. The results show significant improvements ranging from 7% to 33% reduction in the number of active PMs and up to 61% reduction in the number of hourly underutilized PMs.

Conventional multimedia recommender systems treat multimedia as a passive file that plays no role in the computation. In this paper we introduce the concept of Smart multimedia at which the knowledge and the computation required to solve the recommendation problem is transferred to the multimedia itself. Hence, converting the multimedia into an autonomous computational entity that performs its own computation and is responsible for its own decisions concerning where it should be displayed. Our approach utilizes content-based recommendation, where the internal content semantics are captured through semantic level intelligence. Hence, it is very suitable to be used in personalized advertisements.