부산대학교 도서관

The optimal allocation of Communication-Intensive Applications is a well-know complex issue in Clouds. This kind of applications, due to the strong impact of communications on their performance, requires not only that their tasks are allocated on resources able to satisfy their computational requirements but also that the distance among these resources, in terms of communication delay or latency, is the smallest. The allocation strategies currently used, based on a static vision of resources' status, are not suitable for managing effectively the peculiarities of these applications. In this work we propose an innovative allocation strategy that, using information about the sequence of their internal interactions, improves the deployment of Communication-Intensive Applications on available resources. In particular, this strategy allows reducing the number of resources needed for executing each application and, very important, it allows reducing the influence of each application over the performance of the other ones running on the same cloud.