Energy-saving resource scheduling algorithm based on workload characteristic clustering

When infrastructure as a service (IaaS) providers offer high performance services for users, they must think about how to reduce the energy cost of the cloud platform without violating the service level agreement (SLA). A resource scheduling algorithm to ensure SLA was proposed based on clustering analysis of the load characteristic. Ultimately, the targets of reducing SLA violation rate and saving energy were realized. The resource scheduling algorithm was analyzed based on improved K-means clustering analysis and extraction of workload characteristic according to energy consumption. Physical resources were effectively allocated to ensure the requirement of energy saving of IaaS platform. Based on the extension of the CloudSim simulation platform, the algorithm proposed was compared with the optimized best fit decreasing (BFD) to show lower SLA violation rate and energy consumption.