A feedback based prediction model for real time workload in a cloud

• Main Authors: Ghouchani, Babak Esmaeilpour, Abdullah, Azizol, Abdul Hamid, Nor Asila Wati, Abdul Rahman, Amir Rizaan
• Format: Article
• Language: English
• Published: Asian Research Publication Network 2016
• Online Access: http://psasir.upm.edu.my/id/eprint/43495/1/A%20feedback%20based%20prediction%20model%20for%20real%20time%20workload%20in%20a%20cloud.pdf; http://psasir.upm.edu.my/id/eprint/43495/

Most of the distributed systems such as a cloud environment have a nondeterministic structure, and it would cause a serious problem to perform tasks with a time limit. Therefore, many prediction models and performance analyzes being used in the cloud to determine environment for users. Nevertheless, most of these models have a single objective for optimal resource absorption. Which means, they considered just one objective, such as a time limit and other issues are overlooked. In this paper, we proposed a novel model in Cloud to determine environment for the real-time workload. We applied a multi-objective model to absorb optimal resources under reasonable user cost and maximum user sharing. Performance evaluation on CloudSim proves that the new approach outperforms other existing, state-of-the-art methods.