Many-Objective Optimization-Based Task Scheduling in Hybrid Cloud Environments

Due to the security and scalability features of hybrid cloud architecture, it can better meet diverse requirements users for services. And a reasonable resource allocation solution is key adequately utilize cloud. However, most previous studies have not comprehensively optimized performance task scheduling, even ignoring conflicts between its privacy other requirements. Based on above problems, many-objective scheduling optimization model (HCTSO) constructed combining risk rate, utilization, total cost, completion time. Meanwhile, an opposition-based learning knee point-driven evolutionary algorithm (OBL-KnEA) proposed improve solving. The uses generate initial populations faster convergence. Furthermore, perturbation-based multipoint crossover operator dynamic range mutation are designed extend search range. By comparing experiments with excellent algorithms HCTSO, OBL-KnEA achieves results in terms evaluation metrics, populations, effects.