The current state of information technology is to develop and implement new approaches to the computational process. Evaluating the effectiveness of cloud centers is an important challenge for research, but it is complicated by the dynamic of cloud environments and a variety of user requests. This evaluation is vital in cases where virtualization is used to provide well-defined computing resources for users. The proposed model for evaluating the effectiveness of cloud centers in a high degree of virtualization to solve this problem has been proposed. Compared to existing, it considers the ability to service requests for group requests and the distributed time of service requests. The model is based on a two-stage approximation technique. The main non-Markov process is first modeled as an embedded semi-Markov process, then modeled as an approximated Markov process but only when receiving group request flows. The technique of constructing Markov links to build the model has been used. This model provides a full probability distribution of request waiting time, response time to execute requests, and the number of requests in the system. The results show that the performance of cloud centers is highly dependent on the coefficient of variation (CoV), request service time, and the size of the group flow (i.e., the number of requests in the group flow of requests). The larger the flow rate and/or the value of the coefficient of variation of the service time of requests, the longer the response time. But this helps reduce the use of resources by cloud providers. As a result, the work shows that in the conditions of large group flow of requests and/or large value of CoV, it is possible to increase the efficiency of cloud centers by grouping requests using the criterion of homogeneity.
У даній статті порушена проблема доступу до контенту, що знаходиться в географічно віддалених точках, та тривалість його надання кінцевому користувачеві. Встановлено, що для вирішення такого роду задач ефективним є використання CDN мереж, особливо в умовах надання Платформи в якості хмарного сервісу. Проведено дослідження процесів доступу до статичного контенту та тривалість його завантаження в умовах надання PaaS з використанням хмарного сервісу Azure Cloud. Досліджено способи оптимізації доставки статичного контенту з точки зору мінімізації затримки в розгорнутій системі Azure CDN при різних взаємних розташуваннях клієнта і контенту. В результаті проведених досліджень отримано оцінки часових затримок при передаванні статичного контенту, що дозволяють довести ефективність запропонованого методу доступу до контенту, оскільки час завантаження контенту зменшився 4 рази.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.