Nowadays, the grid computing environment faces many difficulties executing new jobs, especially jobs requiring large resource requirements and long execution times. This motivates researchers and scholars to find chea...
详细信息
ISBN:
(数字)9798331523657
ISBN:
(纸本)9798331523664
Nowadays, the grid computing environment faces many difficulties executing new jobs, especially jobs requiring large resource requirements and long execution times. This motivates researchers and scholars to find cheap and fast methods to improve the efficiency of grid environments. One of the cheap and fast methods is to implement job scheduling algorithms based on cheap and fast techniques. This paper proposes a new job ranking backfilling algorithm based on the job's weight and back propagation neural network. To define the weight of the job, first, the proposed model will use a clustering algorithm to cluster the job's dataset into groups, and then the groups will be ranked using an experimental ranking equation. A discrete event simulator is used to validate the proposed algorithm's capability and robustness. The average results revealed that the new algorithm outperforms previous algorithms. The improvement of the studied metrics is between 1.19 and 6.30, respectively. The results proved that the proposed model is efficient and can be used with low overhead in a real environment.
When the finite element analysis of masonry structure are conducted by using micro-model,the stress-strain curves of brick and motar are necessary. 20 sintered shale brick prisms, 20 autoclaved lime-sand brick prisms ...
详细信息
暂无评论