IEEE Access (Jan 2024)
Minimizing Virtual Machine Live Migration Latency for Proactive Fault Tolerance Using an ILP Model With Hybrid Genetic and Simulated Annealing Algorithms
Abstract
Cloud computing has grown significantly in recent years and is now widely used by both individuals and businesses. Cloud service providers need to be prepared for failures to ensure that they can respond to them appropriately by minimizing downtime and achieving business continuity. This can be accomplished through fault tolerance mechanisms which aim to predict, prevent, and recover from failures. One of the common causes of task failures in the cloud is the deterioration of physical machines. If deterioration is detected in the physical machine, the virtual machines (VMs) being hosted must be moved to healthy physical machines. This paper proposes an approach to VM allocation in the event of host deterioration or failure. Namely, an integer linear programming optimization model is proposed for the allocation of the failing VMs while minimizing VM migration time. In addition, hybrid genetic and simulated annealing (HGA and HSA) algorithms are proposed for providing efficient solutions for the optimization model. The HGA is hybridized by a procedure that penalizes infeasible solutions to reduce their chances of being selected in the offspring populations and a hill-climbing procedure that modifies feasible solutions to produce better (or more fit) ones. The HSA starts from a feasible solution and also uses elitism as the HGA in its search to ensure that good candidate solutions are preserved. To validate the quality of the obtained solutions, we compare our approach to the commercial optimization solver CPLEX. In comparison to the CPLEX solver, the results show that for small size data center problems, the proposed HGA and HSA achieve near-optimal solutions with 70.80% and 81.43% increase in speed with an average solution quality trade-off by 20.57% and 78.52%, respectively. Notably, for medium, large and very large size problems the HGA and HSA obtained solutions where the CPLEX solver could not provide solutions within acceptable time. For medium size problems HGA attains solutions with better quality (75.82%) yet with higher execution time (57.27%). For large and very large problems HGA significantly outperforms HSA in terms of solution quality (better by 84.88% and 86.46%) yet with significantly higher execution time (74.22% and 76.55 %), respectively. Thus, the designer may choose which algorithm to use based on whether the focus is on quality or execution time.
Keywords
