A framework for provisioning algorithms as a service

Abstract

Designing, implementing and executing algorithms have become a relevant and important element in various fields. Public users and data researchers are interested in analyzing and interpreting data with shorter execution time and higher performance. Using a scalable and high resource usage environment will help improve algorithm performance. Cloud computing is an environment which provides scalable and high-end virtual resources to achieve high quality services. This thesis presents the design, implementation and evaluation of a framework for provisioning algorithms as a service in the cloud. This framework introduces solutions to help clients overcome different concerns and difficulties, such as looking for an appropriate algorithm, understanding algorithm source code, installing and configuring specific libraries, and achieving high algorithmic performance. The framework provides clients the possibility to discover available algorithms and/or deploy new algorithms over multiple scalable platforms. It also allows clients to analyze data, compare results, and measure algorithm’s performance. A prototype implementation of the framework has been developed to demonstrate the feasibility of the solution. The results of evaluating the prototype demonstrate that providing multiple scalability models and high-end web servers will improve algorithm performance and achieve availability and reliability using the framework.