http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Transmission Performance Comparison and Analysis with Different Publish/Subscribe Protocol
Zujie Fan(판주지에),JaeSoo Kim(김재수) 한국컴퓨터정보학회 2020 한국컴퓨터정보학회 학술발표논문집 Vol.28 No.2
In this paper, we analyze and compare the performance of different publish and subscribe protocols in the real application environment. This paper provides a horizontal comparison of current publish/subscribe protocols in terms of security, throughput, and delay performance. Thanks to the use of lightweight frameworks, the MQTT protocol has demonstrated excellent performance in terms of delay performance. However, the AMQP protocol has more advantages in security and throughput. Although the REST/HTTP protocol has the worst delay performance, it is excellent in terms of compatibility because it is based on the HTTP protocol.
Workload Characterization on a Cloud Platform: An Early Experience
Zujie Ren,Jinxiang Dong,Yongjian Ren,Renjie Zhou,Xindong You 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.6
Understanding the characteristics of cloud workloads is the key to making optimal configuration decisions and improving the system throughput. However workload characterization of cloud, especially in a large-scale production environment, has not been well studied yet. To gain insights on cloud workloads, we collected a one-week workload trace from a 100-node cloud cluster which hosts 1082 virtual machines. We characterized the workload at the granularity of virtual machines and physical nodes, respectively. We concluded with a set of meaningful observations. The results of workload characterization are representative and generally consistent with cloud cluster for public IaaS service providers, which can help other researchers and engineers understand the performance and VM characteristics of the cloud in their production environments.
Performance Evaluation and Modeling Method Research Based on IaaS Cloud Platform
Jian Wan,Xianghong Yang,Zujie Ren,Zheng Ye 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.10
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.