Large scale distributed computing in the cloud

Cloud computing is a rapidly growing paradigm that facilitates the ability for scalable and distributed graph drawing algorithms. Platforms such as Amazon Web Services offer virtually unlimited cloud resources in a pay-as-you-go fashion. Evidently, on demand availability of abundant resources accessible enables large scale processing in a cost-effective approach. There are numerous open source systems that provide distributed graph processing platforms. Frameworks such as Apache Giraph and Spark provide efficient tools for large-scale algorithms. Boundless cloud facilities create opportunities for optimisation methodologies for improving the efficient use of cloud services while concurrently reducing the overall cost. Research projects and business applications have turned towards cloud distributed processing. The ability to remain within budget constraints while maximising execution speeds is of the essence. Optimising resource scheduling and provisioning are the underlying fundamental ways of efficiently maximising processing times while reducing cost. Distributed algorithms such as graph drawing require large computational facilities to process graphs with millions of edges. In this research project, we aim to examine and introduce models to efficiently exploit cloud service abundance using graph drawing algorithms for scheduling and resource provisioning problems.