ELM-Based Intelligent Resource Selection for Grid Scheduling
Guopeng Zhao, Zhiqi Shen, Chunyan Miao · 2009
In Grid computing resource selection is a challenging problem, because Grid scheduler is usually operating in a dynamic and uncertain environment. Conventional scheduling algorithms will fail due to the static rules specified at design time and much user intervention required. Neural networks with a fast and accurate learning paradigm are promising to solve the Grid resource selection problem. This paper first gives the problem formulation, followed by proposing an intelligent resource selection algorithm based on neural networks. Extreme Learning Machine (ELM) was exploited as the learning paradigm due to its fast learning speed and satisfactory performance. Experiments show that ELM is able to provide good prediction for CPU performance, and the proposed scheduling algorithm outperforms a conventional algorithm in terms of computing power utilization.