earticle

영어

With the widespread use of cloud platforms, their performance evaluation tools also have become the research hot spot of academic circle. So far, many performance evaluation tools of the cloud platform have been designed in their corresponding application scenarios, which have brought much convenience on the performance evaluation and management of the cloud platform.
In order to predict the maximum number of virtual machines that can be opened by the cloud platform, this paper integrates the current tools of performance evaluation and proposes a performance evaluation tool based on IaaS cloud platform. The key of the performance evaluation tool is that it not only can evaluate the performance of the cloud platform, but also can predict the maximum number of virtual machines that can be opened by the cloud platform when the configuration of the virtual machine and the workload of each virtual machine have been known. This special performance evaluation tool has not been put forward now. And, the prediction model has been introduced into this tool in this paper that is the most important and core part.
Lastly, to test the effectiveness of cloud platform performance evaluation tool proposed in this paper, some tests have been done on the IaaS cloud platform. According to the contrast results of the forecast error among models, establishing support vector machine and neural network as single forecasting model. The results show combined model can be chosen as the prediction model of cloud platform performance evaluation tool.