A fault-tolerant model for cloud computing environment using seagull-optimized artificial neural network (SOANN)

A fault-tolerant model for cloud computing environment using seagull-optimized artificial neural network (SOANN)

연구 분야: Networking

학회: International Journal of Information Technology

The concept of cloud computing has significantly aided in the development of new application for IT services. However, developing reliable and effective cloud architecture requires a thorough understanding of the recurrent errors, which threatens the system’s operation. Also, there are several issues with the traditional network fault-tolerant data mining technique, including poor accuracy and slow speed. Hence in this paper, we investigate the predictive capability of the proposed fault-tolerant model for cloud based on seagull-optimized artificial neural network (SOANN). The proposed design includes a dual shock controller that is in charge of keeping track of the system’s status and informing it of changes, as well as databases managed by Hadoop and Map Reduce units. The data is gathered to constantly enhance the fault-tolerant prediction system. Lastly, the performance of the proposed model is validated and compared with existing recent studies based on evaluation metrics such as average service time (sec), throughput (requests/min), success rate (%) and availability (%). The experimental findings show that the proposed model outperforms the state-of-the-art approaches in terms of performance.