Task scheduling in cloud environments using MapReduce framework and genetic algorithm
One of the important aspect of cloud computing is processing of amount of big data. MapReduce has been widely used as a powerful data processing model. It has efficiently solved a wide range of large-scale computing problems. MapReduce is a vital programming model for large-scale data processing in the cloud computing, which simplifies the development of traditional distributed program and provides a simple parallel programming method. On the other hand, Task scheduling is critical, which is an NP-completeness problem, plays a critical key role in cloud computing systems. In this paper, we propose a parallel genetic based algorithm to schedule the task on heterogeneous cloud environments. We prompt the algorithm on heterogeneous systems, where resources are of computational and communication heterogeneity. During the implementation of our method, we use Hadoop platform as the backend MapReduce engine. At the last part, through a series of simulation experiments, we prove that our approach has a much better runtime performance than other approach. The main goal of the proposed method is to use MapReduce framework to reduce the overall execution time of the program. The results of tests on a series of directional dag with random input indicate that the proposed method compare with three other existing method in this proposed method the speed of convergence is improved.
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.