A Three-level Scheduler to Execute Scientific Experiments on Federated Clouds

For executing current simulated scientific experiments it is necessary to have huge amounts of computing power. A solution path to this problem is the federated Cloud model, where custom virtual machines (VM) are scheduled in appropriate hosts belonging to different providers to execute such experiments, minimizing response time. In this paper, we study schedulers for federated Clouds. Scheduling is performed at three levels. First, at the broker level, datacenters are selected by their network latencies via three policies ‑Lowest-Latency-Time-First, First-Latency-Time-First, and Latency-Time-In-Round‑. Second, at the infrastructure level, two Cloud VM schedulers based on Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) are implemented. At this level the scheduler is responsible for mapping VMs to datacenter hosts. Finally, at the VM level, jobs are assigned for execution into the preallocated VMs. We evaluate, through simulated experiments, how the proposed three-level scheduler performs w.r.t. the response time delivered to the user as the number of Cloud machines increases, a property known as horizontal scalability.