Published Paper Details:

The era of relying solely on local hard drives for data storage and retrieval has become a thing of the past. Thanks to the swift progress in technology and the global rise of the Internet, computing resources are now more affordable, efficient, and easily available to everyone. It is now easy to experience the convenience of having data storage in the cloud. Thanks to technological advancements alongside the success of the Internet, computers are easily available, less expensive, and more powerful than before. This gave rise to a new age of computing dubbed as "Cloud Computing". In contrast to conventional methods, cloud computing provides cost-effective and flexible services that can easily fulfill complex scientific tasks. To unlock its full power, however, some obstacles need to be tackled like optimizing the scheduling of workflows. Research analyzing this particular issue is abundant, but only a few give attention to cloud specific features such as elasticity and heterogeneity. The available techniques tend not to achieve optimal efficiency in these scenarios. To address this, our study focuses on creating efficient scheduling policies for scientific workflows hosted in an IaaS cloud. In doing so, we design a hybrid algorithm that enhances ACO and PSO to achieve local and global objectives simultaneously.