.png){kind=icon}
.png){kind=icon}
Return
Grid Resource Allocation for Real-Time Data-Intensive Tasks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2017.2760801.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Grid resource allocation mechanism maps tasks to the available grid resources according to some predefined criterion, such as minimizing makespan or execution cost, load balancing, energy efficiency, maintaining user-defined task deadlines, and efficiently using resource memory. The minimization of the makespan is a dominant criterion and is more challenging when computationally intensive tasks have realtime deadlines and data requirements. Such tasks require data files for processing that are transferred from data storage resources to the computing resources, which consume network bandwidth. Resource allocation mechanism for these tasks takes into account the data files transfer time and processing power of the computing resources to complete execution within deadlines. The problem of allocating real-time data intensive tasks to the grid heterogeneous computing resources with the assumption that the data resources are decoupled from the computing resources, remain challenging. This paper addresses the aforementioned problem as the global optimization problem by considering heterogeneous computing resources of various processing capabilities connected to the data storage resources by network links of various bandwidths. We have analytically formulated the resources with the aim to maximize total number of mapped tasks while possibly minimizing the makespan subject to the time QoS constraints of deadlines, execution time, and data files transfer time. The experimental results reveal that the proposed technique outperforms the other alternatives when real-time tasks are considered.
Keywords:
Data-intensive tasks
grid computing
real-time systems
rate-monotonic algorithm
resource allocation mechanism
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W