A Genetic Algorithmic approach for Energy Efficient Task Consolidation in Cloud Computing

In cloud, processing loads arrive from many users at random time instants in the form of task. A proper resource allocation policy attempts to assign this task to available VMs on different host so to complete the execution of the tasks in the shortest possible time with minimum power consumption. The complexity of the resource allocation problem with cloud increases with the number of hosts and becomes difficult to solve effectively. The resource allocation problem is a combinatorial problem and known to be NP-complete. The exponential solution space of the load balancing problem can be searched using heuristic techniques based on Genetic algorithms to obtain a sub - optimal solution in acceptable time. The novel genetic algorithm framework has been proposed for task scheduling to minimize the energy consumption in cloud computing infrastructure. The performance of the proposed GA resource allocation strategy has been compared Random and Round Robin scheduling using in house simulator. The experimental results show that the GA based scheduling model outperforms the existing Random and Round Robin scheduling models.