A dynamic and integrated load-balancing scheduling algorithm for Cloud datacenters

One of the challenging scheduling problems in Cloud datacenters is to take the allocation and migration of reconfigurable virtual machines into consideration as well as the integrated features of hosting physical machines. We introduce a dynamic and integrated resource scheduling algorithm (DAIRS) for Cloud datacenters. Unlike traditional load-balance scheduling algorithms which consider only one factor such as the CPU load in physical servers, DAIRS treats CPU, memory and network bandwidth integrated for both physical machines and virtual machines. We develop integrated measurement for the total imbalance level of a Cloud datacenter as well as the average imbalance level of each server. Simulation results show that DAIRS has good performance with regard to total imbalance level, average imbalance level of each server, as well as overall running time.