Improvement of Task Scheduling with Energy Efficiency including Fault Tolerant with Resilient Computing System in Parallel and Distributed Communication Network
Vijay S. Kumar, P. Madhuri, R. Yamini, Palla Sravani, kamalambika Muthukumar · 2023
In parallel and distributed communication networks, task scheduling is essential for attaining the best system performance. Innovative ways that may intelligently distribute computing resources while minimizing energy consumption and maintaining system resilience are required due to the rising need for energy efficiency and fault tolerance. This system, offers a unique approach to job scheduling in parallel and distributed communication networks that integrate genetic algorithms (GA) and machine learning (ML).Using ML approaches, proposed method analyses historical task execution data to discover patterns that may be applied to task execution time prediction in various computing systems. As a result, this can assign tasks to resources effectively, maximize resource usage, and cut down on execution time as a whole. In addition, using predefined objectives like energy efficiency and fault tolerance, GA is used to find the best task-resource assignments. This applies resilient computing approaches to the job scheduling procedure to overcome problems with fault tolerance. This prevents the execution of crucial operations from being hampered by system faults or resource shortages by utilizing fault detection and recovery technologies. This system can adapt dynamically to shifting network conditions through the combination of ML, GA, and resilient computing, which raises the entire system's reliability and availability.