ISISTAN   23985
INSTITUTO SUPERIOR DE INGENIERIA DEL SOFTWARE
Unidad Ejecutora - UE
congresos y reuniones científicas
Título:
Broker Scheduler based on ACO for Federated Cloud-based Scientific Experiments
Autor/es:
ELINA PACINI; CRISTIAN MATEOS; CARLOS GARCÍA GARINO
Lugar:
CABA
Reunión:
Congreso; ARGENCON 2016; 2016
Institución organizadora:
IEEE Computer Society - Sección Argentina
Resumen:
/* Layout-provided Styles */div.standard {text-align: left;}Federated Clouds are infrastructures arranging physical resources from different datacenters. A Cloud broker intermediates between users and datacenters to support the execution of jobs through Virtual Machines (VM). We exploit federated Clouds to run CPU-intensive jobs from Computational Mechanics, in particular, Parameter Sweep Experiments (PSE). Specifically, we study a broker-level scheduler based on Ant Colony Optimization (ACO), which aims to select the datacenters taking into account both the network latencies and the availability of resources. The less the network latency, the lower the influence on makespan. Moreover, when more VMs can be allocated in datacenters with lower latency, more physical resources can be taken advantage of, and hence job execution time decreases. Then, once our broker-level scheduler has selected a datacenter to execute jobs, VMs are allocated in the physical machines of that datacenter by another intra-datacenter scheduler based on ACO. Experiments performed using CloudSim and job data from a real PSE show that our ACO-based broker-level scheduler succeeds in reducing the makespan compared to similar schedulers based on latency-aware greedy and round robin heuristics.