A resource scheduling method for cloud data centers based on thermal management

Abstract With the rapid growth of cloud computing services, high energy consumption data centers has become a critical concern society. While virtual machine (VM) consolidation is often used to reduce consumption, excessive VM may lead local hot spots and increase risk equipment failure. One possible solution this problem utilize thermal-aware scheduling, but existing approaches have trouble realizing balance between SLA consumption. This paper proposes novel method manage center resources based on thermal management (TM-VMC), which optimizes total proactively prevents from global perspective. Its process includes four phases where VMs scheduler uses an improved ant colony algorithm (UACO) find appropriate target hosts for server temperature utilization status obtained in real-time. Experimental results show that TM-VMC approach can avoid significantly while maintaining low Service Level Agreement (SLA) violation rates compared mainstream algorithms with workloads real-world centers.