An Online Load Balancing Algorithm for Virtual Machine Allocation with Fixed Process Intervals

Abstract

To improve the performance and reliability of resource in Cloud data centers, it is significant to apply load balancing strategy for resource scheduling. In a dynamic changing traffic environment, workload of a Cloud data center has real-time and fixed process time characteristic. One of the challenging scheduling problems in Cloud datacenters is to take the real-time allocation and migration of reconfigurable virtual machines as well as the integrated features of hosting physical machines into consideration. In general, load-balance scheduling is NP-hard problem as proved in many open literatures. We introduce an Online Load-balance Resource Scheduling Algorithm (OLRSA) for Cloud datacenters considering realtime and multi-dimensional resources. Unlike traditional load balance scheduling algorithms which often do not consider lifecycle and fixed interval constraints, OLRSA treats life cycles and fixed intervals for both physical machines and virtual machines. We develop and apply integrated measurement for each server and a Cloud datacenter. New metrics such as integrated imbalance level, capacity makespan, capacity skew are defined for Cloud data centers. Simulation results show that OLRSA has better performance than a few related load balancing algorithms with regard to total imbalance level, makespan, overall load efficiency as well as capacity makespan.