Multi objective Ant Colony Optimization Technique for Task Scheduling in Cloud Computing

Cloud Computing (CC) is a powerful paradigm for accessing IT services over the internet, allowing multiple consumers to share resources. Therefore, it requires task scheduling, allocating, and gradually releasing resources. Hence, efficient Task Scheduling (TS) and Resource Allocation (RA) in cloud systems is crucial to optimize resource usage and ensure timely completion. Assigning computing tasks in a cloud environment is a multifaceted process affected by numerous factors, including network bandwidth availability, completion time, and cost considerations. Traditional scheduling models based on heuristic algorithms have limitations in complex in cloud environments. To tackle these issues, we introduce Multi objective Ant Colony Optimization (MACO) and Adaptive Sequence Dynamic Allocation (ASDA) techniques for TS and RA in the cloud environment. Initially, the tasks submitted globally are divided into long and short queues. After that, the MACO algorithm schedules the task based on queues. Subsequently, the proposed ASDA algorithm efficiently allocates the most appropriate Virtual Machine (VM). If a VM is already occupied, the proposed method promptly chooses the next available VM based on the progress of the work completion process. According to the experimental results, the proposed algorithm achieves significant cost savings compared to other algorithms.