New Deadline-Aware Energy-Consumption Optimization Model and Genetic Algorithm Under Cloud Computing

With large-scale data centers widely deployed around the world, their huge energy consumption becomes a primary concern. Effective resource allocation and scheduling is one of the key to solve this problem. However, existing studies on this topic are relatively rare. In this paper, a new deadline-aware energy-consumption optimization model is designed, which optimizes both the idle and execution energy consumption of servers. To save the idle energy consumption, we propose a new virtual machine deployment algorithm for mapping virtual machines to a constrained packing problem with multidimensional variables. In the proposed genetic algorithm, in order to improve the diversity of the population, we select some of the individuals which do not satisfy time constraints but have low energy consumption into the next generation. To save the execution energy consumption, we adopt the technique of dynamic voltage and frequency scaling. Finally, experimental results show that compared with the existing algorithms, the proposed one greatly reduces the total energy consumption of data centers under the time constraints of tasks.