| Autor: |
Babu, K. Delhi, Kumar, D. Giridhar, Madhusudhan, M. G. |
| Předmět: |
|
| Zdroj: |
International Journal of Advanced Research in Computer Science; Apr2014 Special Issue, Vol. 5 Issue 4, p96-100, 5p |
| Abstrakt: |
With increasing demand for high performance computing and data storage, distributed computing systems have attracted a lot of attention. To have a cost efficient usage of comput ing resources, resource scalability and on demand services are required through virtualization and distributed computing. Service charges and business costs both should known by the service provider for the profit maximization. These are determined by the multi server system configuration and the applications. Optimizations of computing and networking resources need to be jointly performed. The problem of optimal multi server configuration for profit maximization in cloud computing takes such factors as the service provider's margin and profit, the quality of service(QoS), the cost of renting, the cost of energy consumption, the workload of an application, the service level agreement(SLA), the configuration of multi server system, the amount of service. Optimization problem can be formulated and solved analytically by using M/M/m queuing model in multi server system configuration. As a framework to virtual resource mapping , a mixed integer programming(MIP) problem is formulated which relates to cost efficiency of resource mapping procedure. The link mapping can be achieved by multi commodity flow allocation problem. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
